Buckets:
| model,family,task,metric,value | |
| Apertus-v1.5-70B,slds,slds:de_de|0,slds_judge_deepseek_v4_pro,36.03864734299517 | |
| Apertus-v1.5-70B,slds,slds:de_de|0,slds_judge_deepseek_v4_pro_stderr,1.3863094262703322 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,64.73640856672158 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,0.7317313215530418 | |
| Apertus-v1.5-70B,slds,slds:de_it|0,slds_judge_deepseek_v4_pro,37.2463768115942 | |
| Apertus-v1.5-70B,slds,slds:de_it|0,slds_judge_deepseek_v4_pro_stderr,1.7761984632310686 | |
| Apertus-v1.5-70B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score,0.18025078369905956 | |
| Apertus-v1.5-70B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score_stderr,0.015230331974338715 | |
| Apertus-v1.5-70B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score,-0.6332288401253918 | |
| Apertus-v1.5-70B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score_stderr,0.030504693607943875 | |
| Apertus-v1.5-70B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq,0.006269592476489028 | |
| Apertus-v1.5-70B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq_stderr,0.0031274057456725456 | |
| Apertus-v1.5-70B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail,0.003134796238244514 | |
| Apertus-v1.5-70B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail_stderr,0.0022148950918982452 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,57.17462932454695 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,0.9321052482261205 | |
| Apertus-v1.5-70B,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,53.95 | |
| Apertus-v1.5-70B,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,1.6194445043015688 | |
| Apertus-v1.5-70B,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,55.1 | |
| Apertus-v1.5-70B,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,1.111814127121226 | |
| Apertus-v1.5-70B,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro,39.1588785046729 | |
| Apertus-v1.5-70B,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro_stderr,1.9203019113966082 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,71.39209225700165 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.7704644103093325 | |
| Apertus-v1.5-70B,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1,43.73853211009175 | |
| Apertus-v1.5-70B,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1_stderr,1.2985406856823563 | |
| Apertus-v1.5-70B,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,69.56418383518225 | |
| Apertus-v1.5-70B,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.2932099752307547 | |
| Apertus-v1.5-70B,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro,34.48598130841121 | |
| Apertus-v1.5-70B,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro_stderr,2.5063264858922314 | |
| Apertus-v1.5-70B,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1,43.60095011876484 | |
| Apertus-v1.5-70B,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1_stderr,0.5222799895592048 | |
| Apertus-v1.5-70B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score,0.37934362934362936 | |
| Apertus-v1.5-70B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score_stderr,0.015082447815147573 | |
| Apertus-v1.5-70B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score,-0.21138996138996138 | |
| Apertus-v1.5-70B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score_stderr,0.02990147273610741 | |
| Apertus-v1.5-70B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq,0.029922779922779922 | |
| Apertus-v1.5-70B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq_stderr,0.005295828926961814 | |
| Apertus-v1.5-70B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail,0.004826254826254826 | |
| Apertus-v1.5-70B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail_stderr,0.0021541919790751883 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,72.1828665568369 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.7268192844052838 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,48.352553542009886 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.9303901825889968 | |
| Apertus-v1.5-70B,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,70.9878499735869 | |
| Apertus-v1.5-70B,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.25678575516390534 | |
| Apertus-v1.5-70B,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,61.1 | |
| Apertus-v1.5-70B,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.9688360109329125 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,70.51070840197694 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.6926458317892501 | |
| Apertus-v1.5-70B,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,56.3 | |
| Apertus-v1.5-70B,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,1.0897189716555047 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,69.2339373970346 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.7221665181804663 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,64.16803953871499 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.7705359563669429 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,71.75453047775947 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.6987365823680911 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,71.26029654036243 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.7687987145847657 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,66.17792421746293 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.6597987401891766 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,71.14497528830313 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.7295205504773904 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,70.55189456342669 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.6819985066583559 | |
| Apertus-v1.5-70B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score,0.25838926174496646 | |
| Apertus-v1.5-70B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score_stderr,0.014648714200454747 | |
| Apertus-v1.5-70B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score,-0.4608501118568233 | |
| Apertus-v1.5-70B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score_stderr,0.02927350673914225 | |
| Apertus-v1.5-70B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq,0.02237136465324385 | |
| Apertus-v1.5-70B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq_stderr,0.004948886184233456 | |
| Apertus-v1.5-70B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail,0.006711409395973154 | |
| Apertus-v1.5-70B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail_stderr,0.0027322400926222123 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,55.914332784184516 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.9142770796289826 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,65.09060955518946 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.7160057072582067 | |
| Apertus-v1.5-70B,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,71.3338615953513 | |
| Apertus-v1.5-70B,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.3017237161332904 | |
| Apertus-v1.5-70B,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro,32.89719626168224 | |
| Apertus-v1.5-70B,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro_stderr,1.9243740302026444 | |
| Apertus-v1.5-70B,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,57.65 | |
| Apertus-v1.5-70B,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,1.1319425647307566 | |
| Apertus-v1.5-70B,slds,slds:it_de|0,slds_judge_deepseek_v4_pro,39.166666666666664 | |
| Apertus-v1.5-70B,slds,slds:it_de|0,slds_judge_deepseek_v4_pro_stderr,5.833333333333334 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,70.59308072487644 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.6894470135810276 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,70.23887973640856 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.7257511929489153 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,73.40197693574959 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.6406788509022788 | |
| Apertus-v1.5-70B,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,71.0486001056524 | |
| Apertus-v1.5-70B,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.26631500328191593 | |
| Apertus-v1.5-70B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score,0.33076923076923076 | |
| Apertus-v1.5-70B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score_stderr,0.023854795680971114 | |
| Apertus-v1.5-70B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score,-0.3384615384615385 | |
| Apertus-v1.5-70B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score_stderr,0.04770959136194223 | |
| Apertus-v1.5-70B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq,0.0 | |
| Apertus-v1.5-70B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq_stderr,0.0 | |
| Apertus-v1.5-70B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail,0.005128205128205128 | |
| Apertus-v1.5-70B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail_stderr,0.0036215247113446153 | |
| Apertus-v1.5-70B,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,73.68726888536715 | |
| Apertus-v1.5-70B,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.32957548877690096 | |
| Apertus-v1.5-70B,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,73.4838880084522 | |
| Apertus-v1.5-70B,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.2900473619064727 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,64.15156507413509 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.6829665957522167 | |
| Apertus-v1.5-70B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score,0.4911147011308562 | |
| Apertus-v1.5-70B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score_stderr,0.020109773641104244 | |
| Apertus-v1.5-70B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score,0.024232633279483037 | |
| Apertus-v1.5-70B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score_stderr,0.0393599592111639 | |
| Apertus-v1.5-70B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq,0.0420032310177706 | |
| Apertus-v1.5-70B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq_stderr,0.008069174996010682 | |
| Apertus-v1.5-70B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail,0.006462035541195477 | |
| Apertus-v1.5-70B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail_stderr,0.003223165953959458 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,73.08896210873147 | |
| Apertus-v1.5-70B,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.6924659178880829 | |
| Apertus-v1.5-70B,slds,slds:it_it|0,slds_judge_deepseek_v4_pro,45.0 | |
| Apertus-v1.5-70B,slds,slds:it_it|0,slds_judge_deepseek_v4_pro_stderr,5.294365215047318 | |
| Apertus-v1.5-70B,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,57.2 | |
| Apertus-v1.5-70B,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,1.0128818530515802 | |
| Apertus-v1.5-70B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score,0.39015817223198596 | |
| Apertus-v1.5-70B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score_stderr,0.02046702831422059 | |
| Apertus-v1.5-70B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score,-0.1968365553602812 | |
| Apertus-v1.5-70B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score_stderr,0.04064636805964837 | |
| Apertus-v1.5-70B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq,0.022847100175746926 | |
| Apertus-v1.5-70B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq_stderr,0.006269351757562023 | |
| Apertus-v1.5-70B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail,0.0035149384885764497 | |
| Apertus-v1.5-70B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail_stderr,0.002483247992357147 | |
| Apertus-v1.5-70B,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro,40.833333333333336 | |
| Apertus-v1.5-70B,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro_stderr,7.432354875132039 | |
| Apertus-v1.5-70B,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro,37.10144927536232 | |
| Apertus-v1.5-70B,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro_stderr,1.5118070214420727 | |
| DeepSeek-V4-Flash,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,62.4405705229794 | |
| DeepSeek-V4-Flash,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.384054802929149 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,54.505766062602966 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.828768447226729 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,75.00823723228996 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.5947825836038192 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,71.49093904448105 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.7090777728201354 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,72.31466227347612 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.6368228355759701 | |
| DeepSeek-V4-Flash,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score,0.7592891760904685 | |
| DeepSeek-V4-Flash,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score_stderr,0.01719717760966589 | |
| DeepSeek-V4-Flash,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score,0.5605815831987075 | |
| DeepSeek-V4-Flash,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score_stderr,0.032274737321812734 | |
| DeepSeek-V4-Flash,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq,0.0420032310177706 | |
| DeepSeek-V4-Flash,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq_stderr,0.008069174996010675 | |
| DeepSeek-V4-Flash,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail,0.0 | |
| DeepSeek-V4-Flash,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail_stderr,0.0 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,58.77265238879736 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.8196301973617566 | |
| DeepSeek-V4-Flash,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,58.6 | |
| DeepSeek-V4-Flash,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,1.0704810359091854 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,71.79571663920923 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.6814780978882993 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,72.09225700164744 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.6870358870994766 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,59.341021416803954 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.8986715693276888 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,69.06095551894563 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.7309252599173535 | |
| DeepSeek-V4-Flash,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro,54.018691588785046 | |
| DeepSeek-V4-Flash,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro_stderr,2.3637620575658045 | |
| DeepSeek-V4-Flash,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score,0.6153846153846154 | |
| DeepSeek-V4-Flash,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score_stderr,0.024666744915187222 | |
| DeepSeek-V4-Flash,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score,0.2358974358974359 | |
| DeepSeek-V4-Flash,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score_stderr,0.04913713548658782 | |
| DeepSeek-V4-Flash,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq,0.005128205128205128 | |
| DeepSeek-V4-Flash,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq_stderr,0.003621524711344609 | |
| DeepSeek-V4-Flash,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail,0.0 | |
| DeepSeek-V4-Flash,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail_stderr,0.0 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,44.64579901153213 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,0.9147458586473455 | |
| DeepSeek-V4-Flash,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,68.46011621764396 | |
| DeepSeek-V4-Flash,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.37521996987825185 | |
| DeepSeek-V4-Flash,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1,61.03562945368171 | |
| DeepSeek-V4-Flash,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1_stderr,0.5116752206549224 | |
| DeepSeek-V4-Flash,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,50.05 | |
| DeepSeek-V4-Flash,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,1.684241922727066 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,73.27841845140033 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.6410508123066329 | |
| DeepSeek-V4-Flash,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,69.32382461701003 | |
| DeepSeek-V4-Flash,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.3461146917383011 | |
| DeepSeek-V4-Flash,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,52.7 | |
| DeepSeek-V4-Flash,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,1.285227234860098 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,37.12520593080725 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.9206174464202163 | |
| DeepSeek-V4-Flash,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1,65.09174311926606 | |
| DeepSeek-V4-Flash,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1_stderr,1.137718000022771 | |
| DeepSeek-V4-Flash,slds,slds:de_de|0,slds_judge_deepseek_v4_pro,56.08695652173913 | |
| DeepSeek-V4-Flash,slds,slds:de_de|0,slds_judge_deepseek_v4_pro_stderr,1.7495933099476595 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,61.35090609555189 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.7889446108226655 | |
| DeepSeek-V4-Flash,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score,0.3166144200626959 | |
| DeepSeek-V4-Flash,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score_stderr,0.01843013576591813 | |
| DeepSeek-V4-Flash,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score,-0.3557993730407524 | |
| DeepSeek-V4-Flash,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score_stderr,0.03679539548931357 | |
| DeepSeek-V4-Flash,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq,0.0109717868338558 | |
| DeepSeek-V4-Flash,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq_stderr,0.004127369064723157 | |
| DeepSeek-V4-Flash,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail,0.0 | |
| DeepSeek-V4-Flash,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail_stderr,0.0 | |
| DeepSeek-V4-Flash,slds,slds:it_it|0,slds_judge_deepseek_v4_pro,50.0 | |
| DeepSeek-V4-Flash,slds,slds:it_it|0,slds_judge_deepseek_v4_pro_stderr,5.640760748177662 | |
| DeepSeek-V4-Flash,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,65.19809825673534 | |
| DeepSeek-V4-Flash,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.3945458464584993 | |
| DeepSeek-V4-Flash,slds,slds:it_de|0,slds_judge_deepseek_v4_pro,60.0 | |
| DeepSeek-V4-Flash,slds,slds:it_de|0,slds_judge_deepseek_v4_pro_stderr,4.767312946227962 | |
| DeepSeek-V4-Flash,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score,0.37360178970917224 | |
| DeepSeek-V4-Flash,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score_stderr,0.016188402676808756 | |
| DeepSeek-V4-Flash,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score,-0.203579418344519 | |
| DeepSeek-V4-Flash,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score_stderr,0.03191075212206611 | |
| DeepSeek-V4-Flash,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq,0.049217002237136466 | |
| DeepSeek-V4-Flash,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq_stderr,0.007238899594033925 | |
| DeepSeek-V4-Flash,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail,0.0 | |
| DeepSeek-V4-Flash,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail_stderr,0.0 | |
| DeepSeek-V4-Flash,slds,slds:de_it|0,slds_judge_deepseek_v4_pro,43.47826086956522 | |
| DeepSeek-V4-Flash,slds,slds:de_it|0,slds_judge_deepseek_v4_pro_stderr,1.5058603231803644 | |
| DeepSeek-V4-Flash,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,47.45 | |
| DeepSeek-V4-Flash,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,1.6149388961168039 | |
| DeepSeek-V4-Flash,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro,43.333333333333336 | |
| DeepSeek-V4-Flash,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro_stderr,7.212503172976913 | |
| DeepSeek-V4-Flash,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,56.8 | |
| DeepSeek-V4-Flash,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,0.9477823892046287 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,47.34761120263592 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.9347426077122687 | |
| DeepSeek-V4-Flash,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score,0.48166023166023164 | |
| DeepSeek-V4-Flash,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score_stderr,0.015531288442163045 | |
| DeepSeek-V4-Flash,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score,0.04922779922779923 | |
| DeepSeek-V4-Flash,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score_stderr,0.02967894694337175 | |
| DeepSeek-V4-Flash,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq,0.0859073359073359 | |
| DeepSeek-V4-Flash,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq_stderr,0.008710439377517696 | |
| DeepSeek-V4-Flash,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail,0.0 | |
| DeepSeek-V4-Flash,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail_stderr,0.0 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,72.87479406919275 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.6615468223918999 | |
| DeepSeek-V4-Flash,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro,55.14018691588785 | |
| DeepSeek-V4-Flash,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro_stderr,2.6900172237559152 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,71.13673805601319 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.6815508189940161 | |
| DeepSeek-V4-Flash,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score,0.6854130052724078 | |
| DeepSeek-V4-Flash,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score_stderr,0.019483742657673605 | |
| DeepSeek-V4-Flash,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score,0.38488576449912126 | |
| DeepSeek-V4-Flash,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score_stderr,0.038405801955216215 | |
| DeepSeek-V4-Flash,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq,0.014059753954305799 | |
| DeepSeek-V4-Flash,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq_stderr,0.004940148340036701 | |
| DeepSeek-V4-Flash,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail,0.0 | |
| DeepSeek-V4-Flash,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail_stderr,0.0 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,74.82701812191104 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.6222157282109874 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,70.0988467874794 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.7393583750822794 | |
| DeepSeek-V4-Flash,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro,50.193236714975846 | |
| DeepSeek-V4-Flash,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro_stderr,1.6393016627941672 | |
| DeepSeek-V4-Flash,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,65.01056524035921 | |
| DeepSeek-V4-Flash,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.3592898600349878 | |
| DeepSeek-V4-Flash,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro,46.44859813084112 | |
| DeepSeek-V4-Flash,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro_stderr,1.9346233097248517 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,47.79242174629324 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,0.9043252530025403 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,73.60790774299835 | |
| DeepSeek-V4-Flash,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.6467697257532546 | |
| DeepSeek-V4-Flash,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,59.75 | |
| DeepSeek-V4-Flash,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,1.008599955059851 | |
| DeepSeek-V4-Flash,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,63.75066032752245 | |
| DeepSeek-V4-Flash,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.38037510194338525 | |
| DeepSeek-V4-Pro,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,58.65 | |
| DeepSeek-V4-Pro,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,0.8730398000448248 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,72.9654036243822 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.7096153842506515 | |
| DeepSeek-V4-Pro,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,62.6 | |
| DeepSeek-V4-Pro,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.9725891466807571 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,69.04448105436573 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.749621531927475 | |
| DeepSeek-V4-Pro,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1,65.59633027522936 | |
| DeepSeek-V4-Pro,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1_stderr,1.1336524837253161 | |
| DeepSeek-V4-Pro,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,65.97992604331749 | |
| DeepSeek-V4-Pro,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.3613394065051427 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,72.1993410214168 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.7168056033721822 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,70.7495881383855 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.8016812444142087 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,59.16803953871499 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.9050668727306432 | |
| DeepSeek-V4-Pro,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,63.25 | |
| DeepSeek-V4-Pro,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,1.067890185007888 | |
| DeepSeek-V4-Pro,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,63.55 | |
| DeepSeek-V4-Pro,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,1.2992024998738236 | |
| DeepSeek-V4-Pro,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score,0.7851373182552503 | |
| DeepSeek-V4-Pro,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score_stderr,0.01652186497433345 | |
| DeepSeek-V4-Pro,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score,0.6203554119547657 | |
| DeepSeek-V4-Pro,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score_stderr,0.030238490747334586 | |
| DeepSeek-V4-Pro,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq,0.050080775444264945 | |
| DeepSeek-V4-Pro,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq_stderr,0.00877373723155415 | |
| DeepSeek-V4-Pro,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail,0.0 | |
| DeepSeek-V4-Pro,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail_stderr,0.0 | |
| DeepSeek-V4-Pro,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score,0.46332046332046334 | |
| DeepSeek-V4-Pro,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score_stderr,0.015499871016729165 | |
| DeepSeek-V4-Pro,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score,0.023166023166023165 | |
| DeepSeek-V4-Pro,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score_stderr,0.029536487528190526 | |
| DeepSeek-V4-Pro,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq,0.09652509652509653 | |
| DeepSeek-V4-Pro,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq_stderr,0.009179266821885006 | |
| DeepSeek-V4-Pro,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail,0.0 | |
| DeepSeek-V4-Pro,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail_stderr,0.0 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,38.97034596375618 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,1.0226392093633905 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,71.70510708401977 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.7352978186826216 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,44.439868204283364 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.9984325124915836 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,71.30148270181219 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.7453753737642558 | |
| DeepSeek-V4-Pro,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro,54.166666666666664 | |
| DeepSeek-V4-Pro,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro_stderr,6.331538820727852 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,70.35420098846788 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.7373163449369731 | |
| DeepSeek-V4-Pro,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,58.5 | |
| DeepSeek-V4-Pro,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,1.0627309089908992 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,62.87479406919275 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.7614744974148263 | |
| DeepSeek-V4-Pro,slds,slds:it_it|0,slds_judge_deepseek_v4_pro,44.166666666666664 | |
| DeepSeek-V4-Pro,slds,slds:it_it|0,slds_judge_deepseek_v4_pro_stderr,5.1431527492405085 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,70.09060955518946 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.7812922901079706 | |
| DeepSeek-V4-Pro,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,72.78394083465399 | |
| DeepSeek-V4-Pro,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.2982218030944654 | |
| DeepSeek-V4-Pro,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1,61.69121140142518 | |
| DeepSeek-V4-Pro,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1_stderr,0.5196958169726712 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,66.29324546952225 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.8366243959909313 | |
| DeepSeek-V4-Pro,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score,0.3825503355704698 | |
| DeepSeek-V4-Pro,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score_stderr,0.016263699585781784 | |
| DeepSeek-V4-Pro,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score,-0.19910514541387025 | |
| DeepSeek-V4-Pro,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score_stderr,0.03217677512371771 | |
| DeepSeek-V4-Pro,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq,0.035794183445190156 | |
| DeepSeek-V4-Pro,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq_stderr,0.006216778211330348 | |
| DeepSeek-V4-Pro,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail,0.0 | |
| DeepSeek-V4-Pro,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail_stderr,0.0 | |
| DeepSeek-V4-Pro,slds,slds:de_it|0,slds_judge_deepseek_v4_pro,47.00483091787439 | |
| DeepSeek-V4-Pro,slds,slds:de_it|0,slds_judge_deepseek_v4_pro_stderr,1.5201767857701372 | |
| DeepSeek-V4-Pro,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,69.19440042260962 | |
| DeepSeek-V4-Pro,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.29385923325827534 | |
| DeepSeek-V4-Pro,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,67.98468040147914 | |
| DeepSeek-V4-Pro,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.3187031134320379 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,33.311367380560135 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,0.9748659298589003 | |
| DeepSeek-V4-Pro,slds,slds:it_de|0,slds_judge_deepseek_v4_pro,50.833333333333336 | |
| DeepSeek-V4-Pro,slds,slds:it_de|0,slds_judge_deepseek_v4_pro_stderr,5.288399731220373 | |
| DeepSeek-V4-Pro,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score,0.3166144200626959 | |
| DeepSeek-V4-Pro,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score_stderr,0.01843013576591813 | |
| DeepSeek-V4-Pro,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score,-0.3557993730407524 | |
| DeepSeek-V4-Pro,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score_stderr,0.03679539548931357 | |
| DeepSeek-V4-Pro,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq,0.0109717868338558 | |
| DeepSeek-V4-Pro,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq_stderr,0.004127369064723156 | |
| DeepSeek-V4-Pro,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail,0.0 | |
| DeepSeek-V4-Pro,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail_stderr,0.0 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,64.10214168039539 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.7469351461056608 | |
| DeepSeek-V4-Pro,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,73.40200739566825 | |
| DeepSeek-V4-Pro,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.3447928831986319 | |
| DeepSeek-V4-Pro,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro,52.05607476635514 | |
| DeepSeek-V4-Pro,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro_stderr,2.1152573095015086 | |
| DeepSeek-V4-Pro,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score,0.6307692307692307 | |
| DeepSeek-V4-Pro,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score_stderr,0.02446861524147892 | |
| DeepSeek-V4-Pro,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score,0.2692307692307692 | |
| DeepSeek-V4-Pro,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score_stderr,0.048626970131633585 | |
| DeepSeek-V4-Pro,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq,0.007692307692307693 | |
| DeepSeek-V4-Pro,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq_stderr,0.004429724351122427 | |
| DeepSeek-V4-Pro,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail,0.0 | |
| DeepSeek-V4-Pro,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail_stderr,0.0 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,61.73805601317957 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.7762971118161767 | |
| DeepSeek-V4-Pro,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro,54.76635514018692 | |
| DeepSeek-V4-Pro,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro_stderr,2.343104608496452 | |
| DeepSeek-V4-Pro,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score,0.7100175746924429 | |
| DeepSeek-V4-Pro,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score_stderr,0.019039091472153824 | |
| DeepSeek-V4-Pro,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score,0.45342706502636204 | |
| DeepSeek-V4-Pro,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score_stderr,0.03660341276179074 | |
| DeepSeek-V4-Pro,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq,0.033391915641476276 | |
| DeepSeek-V4-Pro,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq_stderr,0.007538270387985197 | |
| DeepSeek-V4-Pro,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail,0.0 | |
| DeepSeek-V4-Pro,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail_stderr,0.0 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,70.46128500823723 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.7804451016136615 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,69.04448105436573 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.7736942064053464 | |
| DeepSeek-V4-Pro,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,60.75 | |
| DeepSeek-V4-Pro,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,1.0608082156317222 | |
| DeepSeek-V4-Pro,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro,47.19626168224299 | |
| DeepSeek-V4-Pro,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro_stderr,2.136228020504238 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,34.093904448105434 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.9667043288449553 | |
| DeepSeek-V4-Pro,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,65.97728473322768 | |
| DeepSeek-V4-Pro,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.36050990743322503 | |
| DeepSeek-V4-Pro,slds,slds:de_de|0,slds_judge_deepseek_v4_pro,53.52657004830918 | |
| DeepSeek-V4-Pro,slds,slds:de_de|0,slds_judge_deepseek_v4_pro_stderr,1.617217785231405 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,71.68863261943987 | |
| DeepSeek-V4-Pro,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.7829195459245835 | |
| DeepSeek-V4-Pro,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro,50.67632850241546 | |
| DeepSeek-V4-Pro,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro_stderr,1.5729625553240958 | |
| GLM-5.2,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,69.12685337726523 | |
| GLM-5.2,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.6693065772516351 | |
| GLM-5.2,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,73.17749603803486 | |
| GLM-5.2,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.3675680977205811 | |
| GLM-5.2,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,58.088962108731465 | |
| GLM-5.2,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,0.8053780198907587 | |
| GLM-5.2,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,58.3 | |
| GLM-5.2,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,0.9513544959080291 | |
| GLM-5.2,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,67.9654036243822 | |
| GLM-5.2,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.6957717806295559 | |
| GLM-5.2,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,71.34266886326195 | |
| GLM-5.2,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.7836448268703501 | |
| GLM-5.2,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,70.50247116968698 | |
| GLM-5.2,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.7327180224065015 | |
| GLM-5.2,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,68.36902800658979 | |
| GLM-5.2,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.8150187042560884 | |
| GLM-5.2,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,55.18121911037891 | |
| GLM-5.2,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,0.828135917032723 | |
| GLM-5.2,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,55.749588138385505 | |
| GLM-5.2,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.7968596283123299 | |
| GLM-5.2,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,60.8 | |
| GLM-5.2,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.9908120622567962 | |
| GLM-5.2,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score,0.6106623586429726 | |
| GLM-5.2,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score_stderr,0.019614151914032707 | |
| GLM-5.2,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score,0.23424878836833601 | |
| GLM-5.2,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score_stderr,0.038838380453137096 | |
| GLM-5.2,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq,0.012924071082390954 | |
| GLM-5.2,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq_stderr,0.0045433972628177765 | |
| GLM-5.2,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail,0.1421647819063005 | |
| GLM-5.2,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail_stderr,0.014047651031448208 | |
| GLM-5.2,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score,0.23197492163009403 | |
| GLM-5.2,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score_stderr,0.016723936228019914 | |
| GLM-5.2,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score,-0.5360501567398119 | |
| GLM-5.2,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score_stderr,0.03344787245603983 | |
| GLM-5.2,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq,0.0 | |
| GLM-5.2,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq_stderr,0.0 | |
| GLM-5.2,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail,0.20532915360501566 | |
| GLM-5.2,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail_stderr,0.016004762452761633 | |
| GLM-5.2,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,72.39703459637562 | |
| GLM-5.2,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.7330567510135461 | |
| GLM-5.2,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,69.9341021416804 | |
| GLM-5.2,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.7661544192114069 | |
| GLM-5.2,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,71.33914421553091 | |
| GLM-5.2,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.3193797983641391 | |
| GLM-5.2,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,70.35420098846788 | |
| GLM-5.2,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.7799254739146769 | |
| GLM-5.2,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,71.10378912685337 | |
| GLM-5.2,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.7699237341898614 | |
| GLM-5.2,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,69.8864236661384 | |
| GLM-5.2,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.31075737529416614 | |
| GLM-5.2,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,67.72652388797364 | |
| GLM-5.2,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.8205633881153517 | |
| GLM-5.2,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro,48.3177570093458 | |
| GLM-5.2,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro_stderr,2.093250109339683 | |
| GLM-5.2,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,59.8 | |
| GLM-5.2,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,0.9872554719190841 | |
| GLM-5.2,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1,60.45871559633027 | |
| GLM-5.2,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1_stderr,1.196475052521447 | |
| GLM-5.2,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro,52.80373831775701 | |
| GLM-5.2,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro_stderr,2.310702799130634 | |
| GLM-5.2,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,59.90939044481054 | |
| GLM-5.2,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.7579988482075305 | |
| GLM-5.2,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,70.35420098846788 | |
| GLM-5.2,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.7391560794831078 | |
| GLM-5.2,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,71.26029654036243 | |
| GLM-5.2,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.7473897721443595 | |
| GLM-5.2,slds,slds:de_de|0,slds_judge_deepseek_v4_pro,55.1207729468599 | |
| GLM-5.2,slds,slds:de_de|0,slds_judge_deepseek_v4_pro_stderr,1.5614906058206808 | |
| GLM-5.2,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,62.5 | |
| GLM-5.2,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,1.122519599497613 | |
| GLM-5.2,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,69.7120972002113 | |
| GLM-5.2,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.3428855234945791 | |
| GLM-5.2,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,69.8283148441627 | |
| GLM-5.2,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.2981903450638791 | |
| GLM-5.2,slds,slds:it_it|0,slds_judge_deepseek_v4_pro,51.666666666666664 | |
| GLM-5.2,slds,slds:it_it|0,slds_judge_deepseek_v4_pro_stderr,3.6583928689847394 | |
| GLM-5.2,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,69.35749588138385 | |
| GLM-5.2,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.8273929482822838 | |
| GLM-5.2,slds,slds:de_it|0,slds_judge_deepseek_v4_pro,43.429951690821255 | |
| GLM-5.2,slds,slds:de_it|0,slds_judge_deepseek_v4_pro_stderr,1.5636874029545496 | |
| GLM-5.2,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro,50.193236714975846 | |
| GLM-5.2,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro_stderr,1.645013917191548 | |
| GLM-5.2,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,72.8995057660626 | |
| GLM-5.2,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.7418366659401167 | |
| GLM-5.2,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score,0.5746924428822495 | |
| GLM-5.2,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score_stderr,0.020744125206719213 | |
| GLM-5.2,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score,0.1827768014059754 | |
| GLM-5.2,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score_stderr,0.040533430934054815 | |
| GLM-5.2,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq,0.033391915641476276 | |
| GLM-5.2,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq_stderr,0.007538270387985233 | |
| GLM-5.2,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail,0.13181019332161686 | |
| GLM-5.2,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail_stderr,0.014194093833360283 | |
| GLM-5.2,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1,57.07838479809976 | |
| GLM-5.2,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1_stderr,0.5722486895168217 | |
| GLM-5.2,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro,56.35514018691589 | |
| GLM-5.2,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro_stderr,2.06315607804438 | |
| GLM-5.2,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,59.35 | |
| GLM-5.2,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.9565366232182597 | |
| GLM-5.2,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score,0.5282051282051282 | |
| GLM-5.2,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score_stderr,0.025310639254933903 | |
| GLM-5.2,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score,0.05641025641025641 | |
| GLM-5.2,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score_stderr,0.050621278509867806 | |
| GLM-5.2,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq,0.0 | |
| GLM-5.2,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq_stderr,0.0 | |
| GLM-5.2,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail,0.12564102564102564 | |
| GLM-5.2,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail_stderr,0.016804895718059373 | |
| GLM-5.2,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,67.42174629324548 | |
| GLM-5.2,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.7398367105265711 | |
| GLM-5.2,slds,slds:it_de|0,slds_judge_deepseek_v4_pro,54.166666666666664 | |
| GLM-5.2,slds,slds:it_de|0,slds_judge_deepseek_v4_pro_stderr,7.633492124853607 | |
| GLM-5.2,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score,0.3232662192393736 | |
| GLM-5.2,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score_stderr,0.01565176650667434 | |
| GLM-5.2,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score,-0.2807606263982103 | |
| GLM-5.2,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score_stderr,0.030824186914281924 | |
| GLM-5.2,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq,0.07270693512304251 | |
| GLM-5.2,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq_stderr,0.008689017969120584 | |
| GLM-5.2,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail,0.21029082774049218 | |
| GLM-5.2,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail_stderr,0.013636974453235468 | |
| GLM-5.2,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,66.04612850082373 | |
| GLM-5.2,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.8638997215671036 | |
| GLM-5.2,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,62.05 | |
| GLM-5.2,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.9277884765863554 | |
| GLM-5.2,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,72.13681986265188 | |
| GLM-5.2,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.34017071882346445 | |
| GLM-5.2,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro,58.333333333333336 | |
| GLM-5.2,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro_stderr,3.445096060879416 | |
| GLM-5.2,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score,0.40444015444015446 | |
| GLM-5.2,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score_stderr,0.015255261733166749 | |
| GLM-5.2,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score,-0.17664092664092665 | |
| GLM-5.2,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score_stderr,0.030365235947725527 | |
| GLM-5.2,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq,0.01447876447876448 | |
| GLM-5.2,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq_stderr,0.0037130309582002865 | |
| GLM-5.2,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail,0.2335907335907336 | |
| GLM-5.2,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail_stderr,0.0131518850349389 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,68.89621087314663 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.6719628379132877 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,69.05271828665569 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.6558475923790981 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,70.28006589785832 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.6465110771255335 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,68.15485996705107 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.8245845303697004 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,42.44645799011532 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.8811823929536136 | |
| Hy-MT2-30B-A3B,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,54.3 | |
| Hy-MT2-30B-A3B,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,1.1129886426163398 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,41.532125205930804 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.9657896165647349 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,69.54695222405272 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.6018765892703951 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,58.89621087314662 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.7358288924842397 | |
| Hy-MT2-30B-A3B,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,54.0 | |
| Hy-MT2-30B-A3B,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,1.1140942644815806 | |
| Hy-MT2-30B-A3B,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,63.24617010036978 | |
| Hy-MT2-30B-A3B,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.301867143594045 | |
| Hy-MT2-30B-A3B,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,70.29318541996831 | |
| Hy-MT2-30B-A3B,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.28932794171330106 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,46.19439868204283 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,0.934872935609063 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,68.54200988467875 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.688336251258852 | |
| Hy-MT2-30B-A3B,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,53.8 | |
| Hy-MT2-30B-A3B,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,1.0455937699021982 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,73.20428336079077 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.5969965077296459 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,62.067545304777596 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.6954964498850273 | |
| Hy-MT2-30B-A3B,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,69.57210776545166 | |
| Hy-MT2-30B-A3B,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.25344881046605533 | |
| Hy-MT2-30B-A3B,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,64.95509772847332 | |
| Hy-MT2-30B-A3B,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.2693769971096686 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,61.69686985172982 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.7257856832342641 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,71.71334431630972 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.6333157708115592 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,69.34102141680395 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.8127250496542057 | |
| Hy-MT2-30B-A3B,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,56.25 | |
| Hy-MT2-30B-A3B,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,1.2205063205047155 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,72.47940691927512 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.6268495968076041 | |
| Hy-MT2-30B-A3B,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,66.55573164289487 | |
| Hy-MT2-30B-A3B,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.2601043947485478 | |
| Hy-MT2-30B-A3B,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,65.0 | |
| Hy-MT2-30B-A3B,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.28158771352915757 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,71.44151565074135 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.6542753455152414 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,51.17792421746293 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,0.9022698458037522 | |
| Hy-MT2-30B-A3B,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,56.75 | |
| Hy-MT2-30B-A3B,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,1.1860527414612043 | |
| Hy-MT2-30B-A3B,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,59.45 | |
| Hy-MT2-30B-A3B,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,1.1992407564621033 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,71.54036243822075 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.7120490755400959 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,60.790774299835256 | |
| Hy-MT2-30B-A3B,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.7479661076102229 | |
| Inkling,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,70.3486529318542 | |
| Inkling,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.28872012789136076 | |
| Inkling,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,63.35 | |
| Inkling,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.9277343125991782 | |
| Inkling,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,71.70510708401977 | |
| Inkling,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.7193318907328854 | |
| Inkling,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,71.52388797364085 | |
| Inkling,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.7327584826815571 | |
| Inkling,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,61.0 | |
| Inkling,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,1.0562092072346445 | |
| Inkling,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,65.65 | |
| Inkling,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.9231187579103961 | |
| Inkling,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,69.31854199683043 | |
| Inkling,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.3108236892880277 | |
| Inkling,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,71.09555189456343 | |
| Inkling,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.7815325290871808 | |
| Inkling,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,58.4 | |
| Inkling,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,1.0061119751462382 | |
| Inkling,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,56.44151565074135 | |
| Inkling,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,0.9107392967125082 | |
| Inkling,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,69.79406919275124 | |
| Inkling,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.647006527766808 | |
| Inkling,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score,0.7715289982425307 | |
| Inkling,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score_stderr,0.017616413756788366 | |
| Inkling,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score,0.5448154657293497 | |
| Inkling,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score_stderr,0.0351410297255533 | |
| Inkling,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq,0.0017574692442882249 | |
| Inkling,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq_stderr,0.0017574692442882186 | |
| Inkling,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail,0.0 | |
| Inkling,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail_stderr,0.0 | |
| Inkling,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,73.49258649093905 | |
| Inkling,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.6664173356506704 | |
| Inkling,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,72.9080824088748 | |
| Inkling,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.3378104523413143 | |
| Inkling,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,73.78088962108731 | |
| Inkling,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.6590161437011264 | |
| Inkling,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,74.02800658978583 | |
| Inkling,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.698756115509777 | |
| Inkling,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,72.33113673805602 | |
| Inkling,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.7344349329535478 | |
| Inkling,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,69.11037891268533 | |
| Inkling,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.8079342049461012 | |
| Inkling,slds,slds:de_it|0,slds_judge_deepseek_v4_pro,44.927536231884055 | |
| Inkling,slds,slds:de_it|0,slds_judge_deepseek_v4_pro_stderr,1.7404783482467352 | |
| Inkling,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score,0.5646718146718147 | |
| Inkling,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score_stderr,0.015411193509852539 | |
| Inkling,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score,0.13320463320463322 | |
| Inkling,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score_stderr,0.030745888878503432 | |
| Inkling,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq,0.003861003861003861 | |
| Inkling,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq_stderr,0.0019277020712612934 | |
| Inkling,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail,0.0028957528957528956 | |
| Inkling,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail_stderr,0.0016702476055035795 | |
| Inkling,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,68.75617792421747 | |
| Inkling,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.7868922148371404 | |
| Inkling,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,73.26994189117802 | |
| Inkling,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.30546512945077925 | |
| Inkling,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro,57.28971962616822 | |
| Inkling,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro_stderr,1.9131656150853518 | |
| Inkling,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro,55.0 | |
| Inkling,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro_stderr,6.215815605080611 | |
| Inkling,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,58.121911037891266 | |
| Inkling,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.866919425556484 | |
| Inkling,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1,65.5249406175772 | |
| Inkling,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1_stderr,0.5331350085005706 | |
| Inkling,slds,slds:de_de|0,slds_judge_deepseek_v4_pro,58.55072463768116 | |
| Inkling,slds,slds:de_de|0,slds_judge_deepseek_v4_pro_stderr,1.5793596310599307 | |
| Inkling,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score,0.676923076923077 | |
| Inkling,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score_stderr,0.02371088850197056 | |
| Inkling,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score,0.3564102564102564 | |
| Inkling,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score_stderr,0.047302766718581996 | |
| Inkling,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq,0.002564102564102564 | |
| Inkling,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq_stderr,0.0025641025641025632 | |
| Inkling,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail,0.002564102564102564 | |
| Inkling,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail_stderr,0.0025641025641025524 | |
| Inkling,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,68.06425041186161 | |
| Inkling,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.6858810961670968 | |
| Inkling,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro,55.265700483091784 | |
| Inkling,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro_stderr,1.6939540951192902 | |
| Inkling,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,59.242174629324545 | |
| Inkling,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,0.8267377147133261 | |
| Inkling,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score,0.4228187919463087 | |
| Inkling,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score_stderr,0.016531318850524467 | |
| Inkling,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score,-0.1487695749440716 | |
| Inkling,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score_stderr,0.03299656862963082 | |
| Inkling,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq,0.005592841163310962 | |
| Inkling,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq_stderr,0.0024955865389942314 | |
| Inkling,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail,0.008948545861297539 | |
| Inkling,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail_stderr,0.003151364266374092 | |
| Inkling,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,56.30971993410214 | |
| Inkling,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.8987451392882698 | |
| Inkling,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,70.7495881383855 | |
| Inkling,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.7352273704114283 | |
| Inkling,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,72.64415156507414 | |
| Inkling,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.7206720525474782 | |
| Inkling,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score,0.3401253918495298 | |
| Inkling,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score_stderr,0.01877070221505746 | |
| Inkling,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score,-0.31974921630094044 | |
| Inkling,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score_stderr,0.03754140443011492 | |
| Inkling,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq,0.0 | |
| Inkling,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq_stderr,0.0 | |
| Inkling,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail,0.0 | |
| Inkling,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail_stderr,0.0 | |
| Inkling,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,68.486529318542 | |
| Inkling,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.30793493851981174 | |
| Inkling,slds,slds:it_de|0,slds_judge_deepseek_v4_pro,59.166666666666664 | |
| Inkling,slds,slds:it_de|0,slds_judge_deepseek_v4_pro_stderr,5.288399731220374 | |
| Inkling,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,64.15 | |
| Inkling,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.8365924543488102 | |
| Inkling,slds,slds:it_it|0,slds_judge_deepseek_v4_pro,44.166666666666664 | |
| Inkling,slds,slds:it_it|0,slds_judge_deepseek_v4_pro_stderr,7.329716739052572 | |
| Inkling,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,69.66227347611202 | |
| Inkling,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.6329539341773934 | |
| Inkling,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,62.6 | |
| Inkling,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,0.9057049782007849 | |
| Inkling,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1,69.79357798165138 | |
| Inkling,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1_stderr,1.170125832495816 | |
| Inkling,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,71.36027469624933 | |
| Inkling,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.27525206714204326 | |
| Inkling,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro,56.44859813084112 | |
| Inkling,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro_stderr,2.223027306324827 | |
| Inkling,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,71.15321252059309 | |
| Inkling,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.719244596568262 | |
| Inkling,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,73.55848434925865 | |
| Inkling,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.6905563537544023 | |
| Inkling,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro,49.4392523364486 | |
| Inkling,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro_stderr,2.169146825189983 | |
| Inkling,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score,0.864297253634895 | |
| Inkling,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score_stderr,0.013776270050171888 | |
| Inkling,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score,0.72859450726979 | |
| Inkling,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score_stderr,0.027552540100343775 | |
| Inkling,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq,0.0 | |
| Inkling,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq_stderr,0.0 | |
| Inkling,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail,0.0 | |
| Inkling,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail_stderr,0.0 | |
| Kimi-K2.6,slds,slds:it_de|0,slds_judge_deepseek_v4_pro,53.333333333333336 | |
| Kimi-K2.6,slds,slds:it_de|0,slds_judge_deepseek_v4_pro_stderr,6.071959063489054 | |
| Kimi-K2.6,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,70.43657331136738 | |
| Kimi-K2.6,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.7996672397050004 | |
| Kimi-K2.6,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,69.08566721581549 | |
| Kimi-K2.6,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.866436423639993 | |
| Kimi-K2.6,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,71.03275224511357 | |
| Kimi-K2.6,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.29228997975825183 | |
| Kimi-K2.6,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score,0.7152899824253075 | |
| Kimi-K2.6,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score_stderr,0.018935129411301297 | |
| Kimi-K2.6,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score,0.43409490333919154 | |
| Kimi-K2.6,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score_stderr,0.03771760050744707 | |
| Kimi-K2.6,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq,0.0035149384885764497 | |
| Kimi-K2.6,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq_stderr,0.002483247992357133 | |
| Kimi-K2.6,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail,0.0017574692442882249 | |
| Kimi-K2.6,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail_stderr,0.0017574692442882099 | |
| Kimi-K2.6,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,67.57001647446458 | |
| Kimi-K2.6,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.7765152685923544 | |
| Kimi-K2.6,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1,59.572446555819475 | |
| Kimi-K2.6,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1_stderr,0.5473388830090338 | |
| Kimi-K2.6,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,70.21658742736398 | |
| Kimi-K2.6,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.2904891024893379 | |
| Kimi-K2.6,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,70.86490939044481 | |
| Kimi-K2.6,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.6969991505667346 | |
| Kimi-K2.6,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,71.07907742998353 | |
| Kimi-K2.6,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.7998446151946259 | |
| Kimi-K2.6,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score,0.274294670846395 | |
| Kimi-K2.6,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score_stderr,0.017677429950568063 | |
| Kimi-K2.6,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score,-0.44200626959247646 | |
| Kimi-K2.6,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score_stderr,0.03533259929417301 | |
| Kimi-K2.6,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq,0.009404388714733543 | |
| Kimi-K2.6,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq_stderr,0.0038242279338255966 | |
| Kimi-K2.6,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail,0.004702194357366771 | |
| Kimi-K2.6,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail_stderr,0.0027105479543554907 | |
| Kimi-K2.6,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,66.83690280065898 | |
| Kimi-K2.6,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.6774645993045697 | |
| Kimi-K2.6,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,72.68357105124142 | |
| Kimi-K2.6,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.33829070088489416 | |
| Kimi-K2.6,slds,slds:de_de|0,slds_judge_deepseek_v4_pro,51.35265700483092 | |
| Kimi-K2.6,slds,slds:de_de|0,slds_judge_deepseek_v4_pro_stderr,1.39532657859429 | |
| Kimi-K2.6,slds,slds:it_it|0,slds_judge_deepseek_v4_pro,45.0 | |
| Kimi-K2.6,slds,slds:it_it|0,slds_judge_deepseek_v4_pro_stderr,5.149286505444373 | |
| Kimi-K2.6,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro,44.57943925233645 | |
| Kimi-K2.6,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro_stderr,2.1464638109600562 | |
| Kimi-K2.6,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,70.16474464579902 | |
| Kimi-K2.6,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.748839994216391 | |
| Kimi-K2.6,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1,68.1651376146789 | |
| Kimi-K2.6,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1_stderr,1.1438092681681675 | |
| Kimi-K2.6,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score,0.525096525096525 | |
| Kimi-K2.6,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score_stderr,0.015522156967874646 | |
| Kimi-K2.6,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score,0.07046332046332046 | |
| Kimi-K2.6,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score_stderr,0.030688786134273782 | |
| Kimi-K2.6,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq,0.02027027027027027 | |
| Kimi-K2.6,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq_stderr,0.0043803895899618365 | |
| Kimi-K2.6,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail,0.010617760617760617 | |
| Kimi-K2.6,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail_stderr,0.0031858721611624954 | |
| Kimi-K2.6,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,71.11202635914333 | |
| Kimi-K2.6,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.7012762741914536 | |
| Kimi-K2.6,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro,53.64485981308411 | |
| Kimi-K2.6,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro_stderr,2.0588781965055514 | |
| Kimi-K2.6,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro,53.333333333333336 | |
| Kimi-K2.6,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro_stderr,5.2704627669473005 | |
| Kimi-K2.6,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,47.059308072487646 | |
| Kimi-K2.6,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.8824790943360572 | |
| Kimi-K2.6,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,70.6836902800659 | |
| Kimi-K2.6,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.7121029644726052 | |
| Kimi-K2.6,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,59.05 | |
| Kimi-K2.6,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.963133234885341 | |
| Kimi-K2.6,slds,slds:de_it|0,slds_judge_deepseek_v4_pro,44.44444444444444 | |
| Kimi-K2.6,slds,slds:de_it|0,slds_judge_deepseek_v4_pro_stderr,1.5230135154259608 | |
| Kimi-K2.6,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,57.55 | |
| Kimi-K2.6,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,1.0012492197250393 | |
| Kimi-K2.6,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,68.29107237189646 | |
| Kimi-K2.6,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.2917620251912709 | |
| Kimi-K2.6,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score,0.3814317673378076 | |
| Kimi-K2.6,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score_stderr,0.01625460824324921 | |
| Kimi-K2.6,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score,-0.2181208053691275 | |
| Kimi-K2.6,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score_stderr,0.03233031600423656 | |
| Kimi-K2.6,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq,0.01901565995525727 | |
| Kimi-K2.6,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq_stderr,0.004570471541746219 | |
| Kimi-K2.6,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail,0.005592841163310962 | |
| Kimi-K2.6,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail_stderr,0.0024955865389942314 | |
| Kimi-K2.6,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro,51.77570093457944 | |
| Kimi-K2.6,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro_stderr,1.7806592552736764 | |
| Kimi-K2.6,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,53.088962108731465 | |
| Kimi-K2.6,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,0.7998573433108651 | |
| Kimi-K2.6,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,72.22405271828666 | |
| Kimi-K2.6,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.7272301059899846 | |
| Kimi-K2.6,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,55.10708401976936 | |
| Kimi-K2.6,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.8364687296623932 | |
| Kimi-K2.6,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score,0.6051282051282051 | |
| Kimi-K2.6,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score_stderr,0.024784316942156378 | |
| Kimi-K2.6,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score,0.2128205128205128 | |
| Kimi-K2.6,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score_stderr,0.04947392465187517 | |
| Kimi-K2.6,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq,0.002564102564102564 | |
| Kimi-K2.6,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq_stderr,0.0025641025641025598 | |
| Kimi-K2.6,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail,0.0 | |
| Kimi-K2.6,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail_stderr,0.0 | |
| Kimi-K2.6,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,69.51664025356577 | |
| Kimi-K2.6,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.28341140962747297 | |
| Kimi-K2.6,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,47.46293245469522 | |
| Kimi-K2.6,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,0.9084841210321825 | |
| Kimi-K2.6,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score,0.8319870759289176 | |
| Kimi-K2.6,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score_stderr,0.015039569244769945 | |
| Kimi-K2.6,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score,0.6865912762520194 | |
| Kimi-K2.6,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score_stderr,0.02861346275405012 | |
| Kimi-K2.6,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq,0.022617124394184167 | |
| Kimi-K2.6,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq_stderr,0.005980766107576115 | |
| Kimi-K2.6,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail,0.0 | |
| Kimi-K2.6,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail_stderr,0.0 | |
| Kimi-K2.6,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,67.39703459637562 | |
| Kimi-K2.6,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.6529232539549689 | |
| Kimi-K2.6,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,73.91268533772653 | |
| Kimi-K2.6,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.6605440812030148 | |
| Kimi-K2.6,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,59.0 | |
| Kimi-K2.6,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,1.0820601976585147 | |
| Kimi-K2.6,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro,50.869565217391305 | |
| Kimi-K2.6,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro_stderr,1.5769691567459483 | |
| Kimi-K2.6,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,66.36738056013179 | |
| Kimi-K2.6,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.7397679043324323 | |
| Kimi-K2.6,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,73.41021416803954 | |
| Kimi-K2.6,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.7083497016909954 | |
| Kimi-K2.6,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,71.83690280065898 | |
| Kimi-K2.6,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.7681942828294835 | |
| Kimi-K2.6,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,68.94083465398838 | |
| Kimi-K2.6,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.2660680118941219 | |
| Kimi-K2.6,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,71.17792421746293 | |
| Kimi-K2.6,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.7170839852471934 | |
| Kimi-K2.6,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,58.65 | |
| Kimi-K2.6,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.991616871629613 | |
| Kimi-K2.6,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,61.7 | |
| Kimi-K2.6,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,1.0052875285585585 | |
| Kimi-K2.6,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,61.35 | |
| Kimi-K2.6,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.9865362481146948 | |
| Kimi-K3,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,71.25205930807249 | |
| Kimi-K3,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.710558482660727 | |
| Kimi-K3,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro,62.71028037383178 | |
| Kimi-K3,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro_stderr,3.0500731884513796 | |
| Kimi-K3,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,69.74464579901154 | |
| Kimi-K3,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.6921247810337811 | |
| Kimi-K3,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,69.46457990115321 | |
| Kimi-K3,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.6852872785407477 | |
| Kimi-K3,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,69.05176967776016 | |
| Kimi-K3,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.30680749376428385 | |
| Kimi-K3,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,70.26359143327842 | |
| Kimi-K3,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.7064460550848802 | |
| Kimi-K3,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,58.95 | |
| Kimi-K3,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.9334582053340847 | |
| Kimi-K3,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,67.61943986820428 | |
| Kimi-K3,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.6786496203550796 | |
| Kimi-K3,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,60.32948929159802 | |
| Kimi-K3,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.6973285577155093 | |
| Kimi-K3,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score,0.5173745173745173 | |
| Kimi-K3,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score_stderr,0.015532360675711534 | |
| Kimi-K3,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score,0.05888030888030888 | |
| Kimi-K3,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score_stderr,0.030651568985144845 | |
| Kimi-K3,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq,0.02413127413127413 | |
| Kimi-K3,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq_stderr,0.004769970046197248 | |
| Kimi-K3,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail,0.027992277992277992 | |
| Kimi-K3,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail_stderr,0.005127241855850647 | |
| Kimi-K3,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,58.45 | |
| Kimi-K3,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,0.8771169653212004 | |
| Kimi-K3,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,68.88797364085667 | |
| Kimi-K3,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.6801382223441075 | |
| Kimi-K3,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,63.85 | |
| Kimi-K3,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.9711349108519248 | |
| Kimi-K3,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score,0.7350565428109854 | |
| Kimi-K3,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score_stderr,0.017751813877042524 | |
| Kimi-K3,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score,0.49596122778675283 | |
| Kimi-K3,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score_stderr,0.0343260192283327 | |
| Kimi-K3,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq,0.025848142164781908 | |
| Kimi-K3,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq_stderr,0.006383131049302914 | |
| Kimi-K3,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail,0.009693053311793215 | |
| Kimi-K3,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail_stderr,0.003941131954526537 | |
| Kimi-K3,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,62.166392092257 | |
| Kimi-K3,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,0.6885744777221589 | |
| Kimi-K3,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,72.1828665568369 | |
| Kimi-K3,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.7098980434675701 | |
| Kimi-K3,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,72.82537067545304 | |
| Kimi-K3,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.7040838082901812 | |
| Kimi-K3,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1,65.30166270783847 | |
| Kimi-K3,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1_stderr,0.597515365417512 | |
| Kimi-K3,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,73.75617792421747 | |
| Kimi-K3,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.682068998984016 | |
| Kimi-K3,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro,58.598130841121495 | |
| Kimi-K3,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro_stderr,2.6070743188114234 | |
| Kimi-K3,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,61.45 | |
| Kimi-K3,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.9334582053340845 | |
| Kimi-K3,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,62.026359143327845 | |
| Kimi-K3,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.7067821790714067 | |
| Kimi-K3,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,70.58901215002642 | |
| Kimi-K3,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.31307688109728665 | |
| Kimi-K3,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,61.65 | |
| Kimi-K3,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.9867909005493697 | |
| Kimi-K3,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score,0.2993730407523511 | |
| Kimi-K3,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score_stderr,0.01814596422399724 | |
| Kimi-K3,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score,-0.3761755485893417 | |
| Kimi-K3,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score_stderr,0.03617100469209733 | |
| Kimi-K3,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq,0.025078369905956112 | |
| Kimi-K3,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq_stderr,0.0061953349123610385 | |
| Kimi-K3,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail,0.014106583072100314 | |
| Kimi-K3,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail_stderr,0.004672573940664172 | |
| Kimi-K3,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro,54.166666666666664 | |
| Kimi-K3,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro_stderr,6.903922176135924 | |
| Kimi-K3,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score,0.6625659050966608 | |
| Kimi-K3,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score_stderr,0.019839688779828786 | |
| Kimi-K3,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score,0.4165202108963093 | |
| Kimi-K3,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score_stderr,0.035975405164938926 | |
| Kimi-K3,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq,0.0913884007029877 | |
| Kimi-K3,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq_stderr,0.0120909523355348 | |
| Kimi-K3,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail,0.0035149384885764497 | |
| Kimi-K3,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail_stderr,0.0024832479923571514 | |
| Kimi-K3,slds,slds:it_de|0,slds_judge_deepseek_v4_pro,43.333333333333336 | |
| Kimi-K3,slds,slds:it_de|0,slds_judge_deepseek_v4_pro_stderr,10.39619199903542 | |
| Kimi-K3,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,70.74135090609555 | |
| Kimi-K3,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.7137224037043243 | |
| Kimi-K3,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,70.49128367670365 | |
| Kimi-K3,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.2797523366047931 | |
| Kimi-K3,slds,slds:de_de|0,slds_judge_deepseek_v4_pro,64.34782608695652 | |
| Kimi-K3,slds,slds:de_de|0,slds_judge_deepseek_v4_pro_stderr,2.127931706480439 | |
| Kimi-K3,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,72.95298468040149 | |
| Kimi-K3,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.3135667721369886 | |
| Kimi-K3,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score,0.383668903803132 | |
| Kimi-K3,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score_stderr,0.016272699747227583 | |
| Kimi-K3,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score,-0.12192393736017897 | |
| Kimi-K3,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score_stderr,0.03129164724860019 | |
| Kimi-K3,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq,0.11073825503355705 | |
| Kimi-K3,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq_stderr,0.010501175421100425 | |
| Kimi-K3,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail,0.021252796420581657 | |
| Kimi-K3,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail_stderr,0.004826336282229856 | |
| Kimi-K3,slds,slds:de_it|0,slds_judge_deepseek_v4_pro,43.28502415458937 | |
| Kimi-K3,slds,slds:de_it|0,slds_judge_deepseek_v4_pro_stderr,2.180614926804984 | |
| Kimi-K3,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,69.90755414685684 | |
| Kimi-K3,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.3036951681769489 | |
| Kimi-K3,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,59.65 | |
| Kimi-K3,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,1.0232903378698985 | |
| Kimi-K3,slds,slds:it_it|0,slds_judge_deepseek_v4_pro,28.333333333333332 | |
| Kimi-K3,slds,slds:it_it|0,slds_judge_deepseek_v4_pro_stderr,8.862017464175613 | |
| Kimi-K3,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,71.22734761120263 | |
| Kimi-K3,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.7653902384217557 | |
| Kimi-K3,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro,43.55140186915888 | |
| Kimi-K3,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro_stderr,3.2723125170297314 | |
| Kimi-K3,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score,0.5256410256410257 | |
| Kimi-K3,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score_stderr,0.025317649726448656 | |
| Kimi-K3,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score,0.07435897435897436 | |
| Kimi-K3,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score_stderr,0.04997155540147398 | |
| Kimi-K3,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq,0.023076923076923078 | |
| Kimi-K3,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq_stderr,0.0076127985014523055 | |
| Kimi-K3,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail,0.002564102564102564 | |
| Kimi-K3,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail_stderr,0.002564102564102548 | |
| Kimi-K3,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,72.94506075013207 | |
| Kimi-K3,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.3566985646678461 | |
| Kimi-K3,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,69.97528830313014 | |
| Kimi-K3,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.7311898892760967 | |
| Kimi-K3,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,68.0477759472817 | |
| Kimi-K3,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.7743003048313444 | |
| Kimi-K3,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,72.97364085667216 | |
| Kimi-K3,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.6650779014386188 | |
| Kimi-K3,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1,51.00917431192661 | |
| Kimi-K3,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1_stderr,1.9136642737878764 | |
| Kimi-K3,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro,60.38647342995169 | |
| Kimi-K3,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro_stderr,1.8272125085675663 | |
| Kimi-K3,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,60.799011532125206 | |
| Kimi-K3,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,0.6760955901229951 | |
| Kimi-K3,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,73.62438220757825 | |
| Kimi-K3,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.6713217143960497 | |
| Kimi-K3,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,73.20428336079077 | |
| Kimi-K3,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.6871098517070707 | |
| LFM2.5-8B-A1B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score,0.3233743409490334 | |
| LFM2.5-8B-A1B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score_stderr,0.019626951170826103 | |
| LFM2.5-8B-A1B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score,-0.2513181019332162 | |
| LFM2.5-8B-A1B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score_stderr,0.03833933908670811 | |
| LFM2.5-8B-A1B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq,0.10193321616871705 | |
| LFM2.5-8B-A1B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq_stderr,0.012695155142907729 | |
| LFM2.5-8B-A1B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail,0.0035149384885764497 | |
| LFM2.5-8B-A1B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail_stderr,0.002483247992357135 | |
| LFM2.5-8B-A1B,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro,16.822429906542055 | |
| LFM2.5-8B-A1B,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro_stderr,1.5968036471393634 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,43.96210873146623 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.8850303930937685 | |
| LFM2.5-8B-A1B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score,0.2080536912751678 | |
| LFM2.5-8B-A1B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score_stderr,0.013583442626021111 | |
| LFM2.5-8B-A1B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score,-0.4608501118568233 | |
| LFM2.5-8B-A1B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score_stderr,0.027280112835850516 | |
| LFM2.5-8B-A1B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq,0.12304250559284116 | |
| LFM2.5-8B-A1B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq_stderr,0.010992364621259352 | |
| LFM2.5-8B-A1B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail,0.006711409395973154 | |
| LFM2.5-8B-A1B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail_stderr,0.002732240092622208 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,50.31301482701812 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.8336814920010119 | |
| LFM2.5-8B-A1B,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,34.35023771790808 | |
| LFM2.5-8B-A1B,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.42530312460517133 | |
| LFM2.5-8B-A1B,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,36.65 | |
| LFM2.5-8B-A1B,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,1.574414623609418 | |
| LFM2.5-8B-A1B,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1,20.489311163895486 | |
| LFM2.5-8B-A1B,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1_stderr,0.4279178873989541 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,56.663920922570014 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.8392458108282579 | |
| LFM2.5-8B-A1B,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,28.65 | |
| LFM2.5-8B-A1B,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,1.3776345249819009 | |
| LFM2.5-8B-A1B,slds,slds:it_it|0,slds_judge_deepseek_v4_pro,10.0 | |
| LFM2.5-8B-A1B,slds,slds:it_it|0,slds_judge_deepseek_v4_pro_stderr,4.438126822992973 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,41.33443163097199 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.954291013444879 | |
| LFM2.5-8B-A1B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score,0.3990306946688207 | |
| LFM2.5-8B-A1B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score_stderr,0.019698586325048895 | |
| LFM2.5-8B-A1B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score,0.0420032310177706 | |
| LFM2.5-8B-A1B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score_stderr,0.03493623148067207 | |
| LFM2.5-8B-A1B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq,0.24394184168012925 | |
| LFM2.5-8B-A1B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq_stderr,0.017275336421484398 | |
| LFM2.5-8B-A1B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail,0.0 | |
| LFM2.5-8B-A1B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail_stderr,0.0 | |
| LFM2.5-8B-A1B,slds,slds:de_de|0,slds_judge_deepseek_v4_pro,16.81159420289855 | |
| LFM2.5-8B-A1B,slds,slds:de_de|0,slds_judge_deepseek_v4_pro_stderr,1.2599740637372594 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,65.1482701812191 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.7567585020613675 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,11.58154859967051 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.5514226042008219 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,64.12685337726523 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.7355074498523486 | |
| LFM2.5-8B-A1B,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,50.240359218172216 | |
| LFM2.5-8B-A1B,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.41708786156275063 | |
| LFM2.5-8B-A1B,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,26.05 | |
| LFM2.5-8B-A1B,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,1.2875466523235386 | |
| LFM2.5-8B-A1B,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,45.882197569994716 | |
| LFM2.5-8B-A1B,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.44344504696487164 | |
| LFM2.5-8B-A1B,slds,slds:it_de|0,slds_judge_deepseek_v4_pro,5.0 | |
| LFM2.5-8B-A1B,slds,slds:it_de|0,slds_judge_deepseek_v4_pro_stderr,2.6111648393354674 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,29.71169686985173 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,0.934502758089519 | |
| LFM2.5-8B-A1B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score,0.25868725868725867 | |
| LFM2.5-8B-A1B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score_stderr,0.013611878901429411 | |
| LFM2.5-8B-A1B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score,-0.2413127413127413 | |
| LFM2.5-8B-A1B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score_stderr,0.02601477505805408 | |
| LFM2.5-8B-A1B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq,0.2413127413127413 | |
| LFM2.5-8B-A1B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq_stderr,0.01329999099897536 | |
| LFM2.5-8B-A1B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail,0.0028957528957528956 | |
| LFM2.5-8B-A1B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail_stderr,0.0016702476055035678 | |
| LFM2.5-8B-A1B,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1,28.53211009174312 | |
| LFM2.5-8B-A1B,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1_stderr,1.176818675844896 | |
| LFM2.5-8B-A1B,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro,10.833333333333334 | |
| LFM2.5-8B-A1B,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro_stderr,4.166666666666667 | |
| LFM2.5-8B-A1B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score,0.2358974358974359 | |
| LFM2.5-8B-A1B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score_stderr,0.021525965407408726 | |
| LFM2.5-8B-A1B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score,-0.5025641025641026 | |
| LFM2.5-8B-A1B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score_stderr,0.043075479195239554 | |
| LFM2.5-8B-A1B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq,0.02564102564102564 | |
| LFM2.5-8B-A1B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq_stderr,0.008014056328139741 | |
| LFM2.5-8B-A1B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail,0.010256410256410256 | |
| LFM2.5-8B-A1B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail_stderr,0.005108392284797563 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,55.362438220757824 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.764200099590765 | |
| LFM2.5-8B-A1B,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro,11.642512077294686 | |
| LFM2.5-8B-A1B,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro_stderr,1.0480857755101838 | |
| LFM2.5-8B-A1B,slds,slds:de_it|0,slds_judge_deepseek_v4_pro,7.246376811594203 | |
| LFM2.5-8B-A1B,slds,slds:de_it|0,slds_judge_deepseek_v4_pro_stderr,0.7522527613976308 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,58.93739703459637 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.7926991630537064 | |
| LFM2.5-8B-A1B,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,27.5 | |
| LFM2.5-8B-A1B,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,1.3313951574670209 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,50.57660626029654 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.8563103414117916 | |
| LFM2.5-8B-A1B,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,32.55 | |
| LFM2.5-8B-A1B,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,1.4579490998966502 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,16.787479406919275 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.6300018183600086 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,15.667215815485998 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.6234673191340986 | |
| LFM2.5-8B-A1B,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro,8.598130841121495 | |
| LFM2.5-8B-A1B,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro_stderr,1.2559054516377333 | |
| LFM2.5-8B-A1B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score,0.11442006269592477 | |
| LFM2.5-8B-A1B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score_stderr,0.012612328071594604 | |
| LFM2.5-8B-A1B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score,-0.7241379310344828 | |
| LFM2.5-8B-A1B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score_stderr,0.02593925742512242 | |
| LFM2.5-8B-A1B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq,0.047021943573667714 | |
| LFM2.5-8B-A1B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq_stderr,0.008387297002877473 | |
| LFM2.5-8B-A1B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail,0.014106583072100314 | |
| LFM2.5-8B-A1B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail_stderr,0.00467257394066417 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,19.497528830313016 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.6756276396957637 | |
| LFM2.5-8B-A1B,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,36.130480718436345 | |
| LFM2.5-8B-A1B,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.44937807089514065 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,20.42833607907743 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.7942601967676978 | |
| LFM2.5-8B-A1B,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro,12.80373831775701 | |
| LFM2.5-8B-A1B,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro_stderr,1.4165457558397698 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,52.17462932454695 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.8272945070091208 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,64.94233937397034 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.6990198795336103 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,53.031301482701814 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.9013019062120473 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,20.485996705107084 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.7959836820648551 | |
| LFM2.5-8B-A1B,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,30.4 | |
| LFM2.5-8B-A1B,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,1.366946492576739 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,28.87973640856672 | |
| LFM2.5-8B-A1B,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,0.9288456774249856 | |
| LFM2.5-8B-A1B,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,44.60644479661912 | |
| LFM2.5-8B-A1B,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.412916194298004 | |
| LFM2.5-8B-A1B,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,40.61278394083465 | |
| LFM2.5-8B-A1B,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.40823490107068733 | |
| Llama-3.3-70B-Instruct,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1,43.027522935779814 | |
| Llama-3.3-70B-Instruct,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1_stderr,1.067686268906462 | |
| Llama-3.3-70B-Instruct,slds,slds:de_it|0,slds_judge_deepseek_v4_pro,14.251207729468598 | |
| Llama-3.3-70B-Instruct,slds,slds:de_it|0,slds_judge_deepseek_v4_pro_stderr,1.3302600820473949 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,44.415156507413506 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,1.004388347384314 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,71.92751235584844 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.6987981819586517 | |
| Llama-3.3-70B-Instruct,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score,0.6413570274636511 | |
| Llama-3.3-70B-Instruct,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score_stderr,0.01929242648604579 | |
| Llama-3.3-70B-Instruct,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score,0.2827140549273021 | |
| Llama-3.3-70B-Instruct,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score_stderr,0.03858485297209158 | |
| Llama-3.3-70B-Instruct,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq_stderr,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail_stderr,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score,0.3974358974358974 | |
| Llama-3.3-70B-Instruct,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score_stderr,0.024811920017903836 | |
| Llama-3.3-70B-Instruct,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score,-0.20512820512820512 | |
| Llama-3.3-70B-Instruct,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score_stderr,0.04962384003580767 | |
| Llama-3.3-70B-Instruct,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq_stderr,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail_stderr,0.0 | |
| Llama-3.3-70B-Instruct,slds,slds:it_it|0,slds_judge_deepseek_v4_pro,10.833333333333334 | |
| Llama-3.3-70B-Instruct,slds,slds:it_it|0,slds_judge_deepseek_v4_pro_stderr,5.961789101681584 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,67.24052718286656 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.7239829401024513 | |
| Llama-3.3-70B-Instruct,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,66.3365029054411 | |
| Llama-3.3-70B-Instruct,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.29395947415891677 | |
| Llama-3.3-70B-Instruct,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,56.45 | |
| Llama-3.3-70B-Instruct,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,1.4732071123843704 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,72.92421746293246 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.6409274600867677 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,71.96046128500824 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.7274817393062156 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,60.45304777594728 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.7046824252553772 | |
| Llama-3.3-70B-Instruct,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score,0.507908611599297 | |
| Llama-3.3-70B-Instruct,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score_stderr,0.020976909415623825 | |
| Llama-3.3-70B-Instruct,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score,0.015817223198594025 | |
| Llama-3.3-70B-Instruct,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score_stderr,0.04195381883124765 | |
| Llama-3.3-70B-Instruct,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq_stderr,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail_stderr,0.0 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,68.20428336079077 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.6892068161817485 | |
| Llama-3.3-70B-Instruct,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro,14.166666666666666 | |
| Llama-3.3-70B-Instruct,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro_stderr,7.633492124853607 | |
| Llama-3.3-70B-Instruct,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro,19.439252336448597 | |
| Llama-3.3-70B-Instruct,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro_stderr,2.2916890612216085 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,59.01976935749588 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.728507559323646 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,57.26523887973641 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.7554999420131948 | |
| Llama-3.3-70B-Instruct,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,71.69043845747491 | |
| Llama-3.3-70B-Instruct,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.29940395515625934 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,68.13838550247117 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.6774340482127014 | |
| Llama-3.3-70B-Instruct,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro,14.672897196261681 | |
| Llama-3.3-70B-Instruct,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro_stderr,1.9844118187593465 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,48.73970345963756 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.8921869791503415 | |
| Llama-3.3-70B-Instruct,slds,slds:de_de|0,slds_judge_deepseek_v4_pro,21.256038647342994 | |
| Llama-3.3-70B-Instruct,slds,slds:de_de|0,slds_judge_deepseek_v4_pro_stderr,1.678049143247529 | |
| Llama-3.3-70B-Instruct,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro,18.411214953271028 | |
| Llama-3.3-70B-Instruct,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro_stderr,2.364842459308723 | |
| Llama-3.3-70B-Instruct,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,44.95 | |
| Llama-3.3-70B-Instruct,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,1.394528972548217 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,71.60626029654036 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.7148798733459936 | |
| Llama-3.3-70B-Instruct,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1,37.36817102137767 | |
| Llama-3.3-70B-Instruct,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1_stderr,0.45139355931826325 | |
| Llama-3.3-70B-Instruct,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,70.91389329107237 | |
| Llama-3.3-70B-Instruct,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.32487443210409045 | |
| Llama-3.3-70B-Instruct,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,65.08716323296355 | |
| Llama-3.3-70B-Instruct,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.30604747880028405 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,58.40197693574959 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.7685902669921695 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,69.62108731466228 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.697210468847721 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,66.83690280065898 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.7090070466881302 | |
| Llama-3.3-70B-Instruct,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,51.4 | |
| Llama-3.3-70B-Instruct,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,1.2421411243752933 | |
| Llama-3.3-70B-Instruct,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score,0.44787644787644787 | |
| Llama-3.3-70B-Instruct,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score_stderr,0.015457066464405433 | |
| Llama-3.3-70B-Instruct,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score,-0.10328185328185328 | |
| Llama-3.3-70B-Instruct,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score_stderr,0.030902177085374596 | |
| Llama-3.3-70B-Instruct,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq,0.0009652509652509653 | |
| Llama-3.3-70B-Instruct,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq_stderr,0.000965250965250966 | |
| Llama-3.3-70B-Instruct,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail,0.007722007722007722 | |
| Llama-3.3-70B-Instruct,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail_stderr,0.0027208939847200735 | |
| Llama-3.3-70B-Instruct,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score,0.31208053691275167 | |
| Llama-3.3-70B-Instruct,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score_stderr,0.015505165681607841 | |
| Llama-3.3-70B-Instruct,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score,-0.37583892617449666 | |
| Llama-3.3-70B-Instruct,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score_stderr,0.031010331363215682 | |
| Llama-3.3-70B-Instruct,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq_stderr,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail_stderr,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score,0.2335423197492163 | |
| Llama-3.3-70B-Instruct,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score_stderr,0.01676320935294393 | |
| Llama-3.3-70B-Instruct,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score,-0.5329153605015674 | |
| Llama-3.3-70B-Instruct,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score_stderr,0.03352641870588786 | |
| Llama-3.3-70B-Instruct,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq_stderr,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail,0.0 | |
| Llama-3.3-70B-Instruct,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail_stderr,0.0 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,71.21087314662273 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.7460020810031436 | |
| Llama-3.3-70B-Instruct,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,53.8 | |
| Llama-3.3-70B-Instruct,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,1.3590567228336723 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,72.22405271828666 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.6454021270833479 | |
| Llama-3.3-70B-Instruct,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,67.13681986265188 | |
| Llama-3.3-70B-Instruct,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.31020806166624987 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,42.26523887973641 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,0.9776421581142943 | |
| Llama-3.3-70B-Instruct,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,48.95 | |
| Llama-3.3-70B-Instruct,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,1.2080082448385825 | |
| Llama-3.3-70B-Instruct,slds,slds:it_de|0,slds_judge_deepseek_v4_pro,16.666666666666668 | |
| Llama-3.3-70B-Instruct,slds,slds:it_de|0,slds_judge_deepseek_v4_pro_stderr,8.73284754605428 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,45.609555189456344 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.9775130689844798 | |
| Llama-3.3-70B-Instruct,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,52.0 | |
| Llama-3.3-70B-Instruct,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,1.140836332559777 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,70.7660626029654 | |
| Llama-3.3-70B-Instruct,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.751926196371494 | |
| Llama-3.3-70B-Instruct,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro,15.217391304347826 | |
| Llama-3.3-70B-Instruct,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro_stderr,1.3965358237120622 | |
| Llama-3.3-70B-Instruct,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,67.54622292657157 | |
| Llama-3.3-70B-Instruct,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.27354942076940686 | |
| MiniMax-M3,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro,52.1256038647343 | |
| MiniMax-M3,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro_stderr,1.7397426601936536 | |
| MiniMax-M3,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro,50.0 | |
| MiniMax-M3,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro_stderr,6.628679652796169 | |
| MiniMax-M3,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,66.49762282091918 | |
| MiniMax-M3,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.3595916488337117 | |
| MiniMax-M3,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,71.54036243822075 | |
| MiniMax-M3,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.7728721996905152 | |
| MiniMax-M3,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,70.88138385502471 | |
| MiniMax-M3,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.7675545405361759 | |
| MiniMax-M3,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,68.5667215815486 | |
| MiniMax-M3,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.7664696138545444 | |
| MiniMax-M3,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1,67.4770642201835 | |
| MiniMax-M3,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1_stderr,1.1389418328378351 | |
| MiniMax-M3,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,71.63097199341021 | |
| MiniMax-M3,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.6731995484894464 | |
| MiniMax-M3,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,56.0 | |
| MiniMax-M3,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,0.951063937422362 | |
| MiniMax-M3,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,59.8 | |
| MiniMax-M3,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,1.0513451541553 | |
| MiniMax-M3,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,70.47775947281713 | |
| MiniMax-M3,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.701530000820164 | |
| MiniMax-M3,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score,0.680140597539543 | |
| MiniMax-M3,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score_stderr,0.019570627113877904 | |
| MiniMax-M3,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score,0.4112478031634446 | |
| MiniMax-M3,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score_stderr,0.03705507502422364 | |
| MiniMax-M3,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq,0.050966608084358524 | |
| MiniMax-M3,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq_stderr,0.009228039495519643 | |
| MiniMax-M3,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail,0.007029876977152899 | |
| MiniMax-M3,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail_stderr,0.003505643791420053 | |
| MiniMax-M3,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,43.5831960461285 | |
| MiniMax-M3,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.9430795800882134 | |
| MiniMax-M3,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro,53.271028037383175 | |
| MiniMax-M3,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro_stderr,2.5912229976943855 | |
| MiniMax-M3,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score,0.4777992277992278 | |
| MiniMax-M3,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score_stderr,0.015526418990864956 | |
| MiniMax-M3,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score,-0.006756756756756757 | |
| MiniMax-M3,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score_stderr,0.030492092244746923 | |
| MiniMax-M3,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq,0.037644787644787646 | |
| MiniMax-M3,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq_stderr,0.00591629679251854 | |
| MiniMax-M3,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail,0.06660231660231661 | |
| MiniMax-M3,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail_stderr,0.00775010974056759 | |
| MiniMax-M3,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,65.48071843634443 | |
| MiniMax-M3,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.34717219595891363 | |
| MiniMax-M3,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score,0.32102908277404923 | |
| MiniMax-M3,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score_stderr,0.015623273863438076 | |
| MiniMax-M3,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score,-0.25727069351230425 | |
| MiniMax-M3,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score_stderr,0.03054452900796045 | |
| MiniMax-M3,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq,0.10067114093959731 | |
| MiniMax-M3,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq_stderr,0.01006899281266496 | |
| MiniMax-M3,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail,0.020134228187919462 | |
| MiniMax-M3,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail_stderr,0.004700294365849883 | |
| MiniMax-M3,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro,54.953271028037385 | |
| MiniMax-M3,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro_stderr,2.3167215165744155 | |
| MiniMax-M3,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,50.691927512355846 | |
| MiniMax-M3,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,0.865076977455187 | |
| MiniMax-M3,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,64.26571579503434 | |
| MiniMax-M3,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.3841601359553392 | |
| MiniMax-M3,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,62.95 | |
| MiniMax-M3,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,1.0070043639154311 | |
| MiniMax-M3,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,71.92751235584844 | |
| MiniMax-M3,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.7180653788000259 | |
| MiniMax-M3,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,73.69851729818781 | |
| MiniMax-M3,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.6808840961392106 | |
| MiniMax-M3,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,67.29001584786054 | |
| MiniMax-M3,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.3592069142968208 | |
| MiniMax-M3,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,70.95551894563427 | |
| MiniMax-M3,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.6879278163061312 | |
| MiniMax-M3,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,68.93739703459637 | |
| MiniMax-M3,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.788318053786483 | |
| MiniMax-M3,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score,0.7705977382875606 | |
| MiniMax-M3,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score_stderr,0.0169129153476294 | |
| MiniMax-M3,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score,0.5735056542810986 | |
| MiniMax-M3,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score_stderr,0.032150059938481544 | |
| MiniMax-M3,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq,0.03231017770597738 | |
| MiniMax-M3,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq_stderr,0.007112847908984973 | |
| MiniMax-M3,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail,0.024232633279483037 | |
| MiniMax-M3,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail_stderr,0.006185562682730043 | |
| MiniMax-M3,slds,slds:it_de|0,slds_judge_deepseek_v4_pro,45.833333333333336 | |
| MiniMax-M3,slds,slds:it_de|0,slds_judge_deepseek_v4_pro_stderr,7.012794944192574 | |
| MiniMax-M3,slds,slds:it_it|0,slds_judge_deepseek_v4_pro,38.333333333333336 | |
| MiniMax-M3,slds,slds:it_it|0,slds_judge_deepseek_v4_pro_stderr,8.241922890278271 | |
| MiniMax-M3,slds,slds:de_de|0,slds_judge_deepseek_v4_pro,57.82608695652174 | |
| MiniMax-M3,slds,slds:de_de|0,slds_judge_deepseek_v4_pro_stderr,1.7265975883187312 | |
| MiniMax-M3,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score,0.5205128205128206 | |
| MiniMax-M3,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score_stderr,0.025329663163489943 | |
| MiniMax-M3,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score,0.041025641025641026 | |
| MiniMax-M3,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score_stderr,0.050659326326979885 | |
| MiniMax-M3,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq,0.0 | |
| MiniMax-M3,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq_stderr,0.0 | |
| MiniMax-M3,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail,0.010256410256410256 | |
| MiniMax-M3,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail_stderr,0.005108392284797563 | |
| MiniMax-M3,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,49.64579901153213 | |
| MiniMax-M3,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.910709599799367 | |
| MiniMax-M3,slds,slds:de_it|0,slds_judge_deepseek_v4_pro,45.7487922705314 | |
| MiniMax-M3,slds,slds:de_it|0,slds_judge_deepseek_v4_pro_stderr,1.5531100621973666 | |
| MiniMax-M3,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,71.18616144975289 | |
| MiniMax-M3,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.6986049195516264 | |
| MiniMax-M3,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,67.15815485996706 | |
| MiniMax-M3,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.6814832280175375 | |
| MiniMax-M3,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score,0.2727272727272727 | |
| MiniMax-M3,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score_stderr,0.01764587585679886 | |
| MiniMax-M3,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score,-0.445141065830721 | |
| MiniMax-M3,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score_stderr,0.035270763456187584 | |
| MiniMax-M3,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq,0.009404388714733543 | |
| MiniMax-M3,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq_stderr,0.003824227933825593 | |
| MiniMax-M3,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail,0.01567398119122257 | |
| MiniMax-M3,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail_stderr,0.004921408635637977 | |
| MiniMax-M3,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,72.64415156507414 | |
| MiniMax-M3,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.6931990115158793 | |
| MiniMax-M3,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,62.55 | |
| MiniMax-M3,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.9510573327887519 | |
| MiniMax-M3,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,69.79406919275124 | |
| MiniMax-M3,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.7759540465250955 | |
| MiniMax-M3,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,47.915980230642504 | |
| MiniMax-M3,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,0.895854106978399 | |
| MiniMax-M3,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,73.37726523887973 | |
| MiniMax-M3,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.6589169538648572 | |
| MiniMax-M3,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,68.69783412572636 | |
| MiniMax-M3,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.3637709568783095 | |
| MiniMax-M3,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,65.6836902800659 | |
| MiniMax-M3,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.6701725233663398 | |
| MiniMax-M3,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,69.70153195985209 | |
| MiniMax-M3,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.40060675598629536 | |
| MiniMax-M3,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1,59.296912114014255 | |
| MiniMax-M3,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1_stderr,0.5394742330038497 | |
| MiniMax-M3,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,56.4 | |
| MiniMax-M3,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,1.0051125590108818 | |
| MiniMax-M3,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,66.26029654036243 | |
| MiniMax-M3,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.6880907478772719 | |
| MiniMax-M3,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro,47.850467289719624 | |
| MiniMax-M3,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro_stderr,2.330586898516985 | |
| MiniMax-M3,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,56.95 | |
| MiniMax-M3,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,1.068501745389074 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,51.30971993410214 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.7492255267899977 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,35.387149917627674 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.9216131097339681 | |
| Mistral-Medium-3.5-128B,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro,24.166666666666668 | |
| Mistral-Medium-3.5-128B,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro_stderr,5.429762723390704 | |
| Mistral-Medium-3.5-128B,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,48.95 | |
| Mistral-Medium-3.5-128B,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,1.130654410943029 | |
| Mistral-Medium-3.5-128B,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,64.56154252509245 | |
| Mistral-Medium-3.5-128B,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.2908371960046153 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,32.47116968698517 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.9621391639716651 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,67.38879736408566 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.6638808304030379 | |
| Mistral-Medium-3.5-128B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score,0.26489028213166144 | |
| Mistral-Medium-3.5-128B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score_stderr,0.017483942871732938 | |
| Mistral-Medium-3.5-128B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score,-0.46551724137931033 | |
| Mistral-Medium-3.5-128B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score_stderr,0.034961102036496695 | |
| Mistral-Medium-3.5-128B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq,0.004702194357366771 | |
| Mistral-Medium-3.5-128B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq_stderr,0.0027105479543554946 | |
| Mistral-Medium-3.5-128B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail,0.004702194357366771 | |
| Mistral-Medium-3.5-128B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail_stderr,0.002710547954355482 | |
| Mistral-Medium-3.5-128B,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,50.55 | |
| Mistral-Medium-3.5-128B,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,1.2117463206994443 | |
| Mistral-Medium-3.5-128B,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro,38.03738317757009 | |
| Mistral-Medium-3.5-128B,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro_stderr,2.080377681689983 | |
| Mistral-Medium-3.5-128B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score,0.3422818791946309 | |
| Mistral-Medium-3.5-128B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score_stderr,0.015877646480153794 | |
| Mistral-Medium-3.5-128B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score,-0.2975391498881432 | |
| Mistral-Medium-3.5-128B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score_stderr,0.03163292688542229 | |
| Mistral-Medium-3.5-128B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq,0.017897091722595078 | |
| Mistral-Medium-3.5-128B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq_stderr,0.004436535909240919 | |
| Mistral-Medium-3.5-128B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail,0.011185682326621925 | |
| Mistral-Medium-3.5-128B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail_stderr,0.003519353440936077 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,71.05436573311367 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.6354642429807364 | |
| Mistral-Medium-3.5-128B,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1,54.4954128440367 | |
| Mistral-Medium-3.5-128B,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1_stderr,1.4884507238899543 | |
| Mistral-Medium-3.5-128B,slds,slds:de_de|0,slds_judge_deepseek_v4_pro,39.42028985507246 | |
| Mistral-Medium-3.5-128B,slds,slds:de_de|0,slds_judge_deepseek_v4_pro_stderr,1.3776444719649932 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,67.15815485996706 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.8422773966101414 | |
| Mistral-Medium-3.5-128B,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro,28.985507246376812 | |
| Mistral-Medium-3.5-128B,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro_stderr,1.5335694305124272 | |
| Mistral-Medium-3.5-128B,slds,slds:it_de|0,slds_judge_deepseek_v4_pro,33.333333333333336 | |
| Mistral-Medium-3.5-128B,slds,slds:it_de|0,slds_judge_deepseek_v4_pro_stderr,8.28775414010748 | |
| Mistral-Medium-3.5-128B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score,0.47876447876447875 | |
| Mistral-Medium-3.5-128B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score_stderr,0.015527723457911214 | |
| Mistral-Medium-3.5-128B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score,-0.0028957528957528956 | |
| Mistral-Medium-3.5-128B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score_stderr,0.03046208263233823 | |
| Mistral-Medium-3.5-128B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq,0.03957528957528957 | |
| Mistral-Medium-3.5-128B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq_stderr,0.006060012757302423 | |
| Mistral-Medium-3.5-128B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail,0.010617760617760617 | |
| Mistral-Medium-3.5-128B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail_stderr,0.00318587216116249 | |
| Mistral-Medium-3.5-128B,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro,32.429906542056074 | |
| Mistral-Medium-3.5-128B,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro_stderr,1.9509101615375668 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,67.8500823723229 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.6166107801832333 | |
| Mistral-Medium-3.5-128B,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,55.0 | |
| Mistral-Medium-3.5-128B,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,1.2298629249108826 | |
| Mistral-Medium-3.5-128B,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,55.1 | |
| Mistral-Medium-3.5-128B,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,1.2092399706148755 | |
| Mistral-Medium-3.5-128B,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1,51.13064133016627 | |
| Mistral-Medium-3.5-128B,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1_stderr,0.563376602284235 | |
| Mistral-Medium-3.5-128B,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,62.432646592709986 | |
| Mistral-Medium-3.5-128B,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.28655551237178833 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,55.11532125205931 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.7868542537789838 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,67.25700164744646 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.6302683514784697 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,68.25370675453048 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.7683242859756858 | |
| Mistral-Medium-3.5-128B,slds,slds:de_it|0,slds_judge_deepseek_v4_pro,28.067632850241544 | |
| Mistral-Medium-3.5-128B,slds,slds:de_it|0,slds_judge_deepseek_v4_pro_stderr,1.4120815572683103 | |
| Mistral-Medium-3.5-128B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score,0.48205128205128206 | |
| Mistral-Medium-3.5-128B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score_stderr,0.025334667080954915 | |
| Mistral-Medium-3.5-128B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score,-0.03076923076923077 | |
| Mistral-Medium-3.5-128B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score_stderr,0.050547771934900114 | |
| Mistral-Medium-3.5-128B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq,0.005128205128205128 | |
| Mistral-Medium-3.5-128B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq_stderr,0.0036215247113446153 | |
| Mistral-Medium-3.5-128B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail,0.020512820512820513 | |
| Mistral-Medium-3.5-128B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail_stderr,0.007186828266574732 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,53.39373970345964 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.8316984365956577 | |
| Mistral-Medium-3.5-128B,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,53.2 | |
| Mistral-Medium-3.5-128B,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,1.1022133966974343 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,31.194398682042834 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,0.9733600749084779 | |
| Mistral-Medium-3.5-128B,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,49.95 | |
| Mistral-Medium-3.5-128B,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,1.241043287807101 | |
| Mistral-Medium-3.5-128B,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,70.98256735340729 | |
| Mistral-Medium-3.5-128B,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.28105375181973463 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,68.65733113673805 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.7761565886987564 | |
| Mistral-Medium-3.5-128B,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,67.51980982567353 | |
| Mistral-Medium-3.5-128B,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.32059021660696985 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,56.74629324546952 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.7491486228174696 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,68.08896210873147 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.6699616523530386 | |
| Mistral-Medium-3.5-128B,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,64.31325937665082 | |
| Mistral-Medium-3.5-128B,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.2930532791059848 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,64.80230642504118 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.6301265104171405 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,68.17133443163097 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.6827996560540588 | |
| Mistral-Medium-3.5-128B,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro,39.626168224299064 | |
| Mistral-Medium-3.5-128B,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro_stderr,2.1450045456546722 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,34.67874794069193 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,0.9417507037525205 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,68.60790774299835 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.6694450050349293 | |
| Mistral-Medium-3.5-128B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score,0.6720516962843296 | |
| Mistral-Medium-3.5-128B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score_stderr,0.01888468728692798 | |
| Mistral-Medium-3.5-128B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score,0.3861066235864297 | |
| Mistral-Medium-3.5-128B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score_stderr,0.03617913102006719 | |
| Mistral-Medium-3.5-128B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq,0.0420032310177706 | |
| Mistral-Medium-3.5-128B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq_stderr,0.008069174996010665 | |
| Mistral-Medium-3.5-128B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail,0.0420032310177706 | |
| Mistral-Medium-3.5-128B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail_stderr,0.008069174996010696 | |
| Mistral-Medium-3.5-128B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score,0.5782073813708261 | |
| Mistral-Medium-3.5-128B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score_stderr,0.020721306544057894 | |
| Mistral-Medium-3.5-128B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score,0.1968365553602812 | |
| Mistral-Medium-3.5-128B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score_stderr,0.04026395256933613 | |
| Mistral-Medium-3.5-128B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq,0.040421792618629174 | |
| Mistral-Medium-3.5-128B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq_stderr,0.00826368596995804 | |
| Mistral-Medium-3.5-128B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail,0.026362038664323375 | |
| Mistral-Medium-3.5-128B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail_stderr,0.006722240988806605 | |
| Mistral-Medium-3.5-128B,slds,slds:it_it|0,slds_judge_deepseek_v4_pro,41.666666666666664 | |
| Mistral-Medium-3.5-128B,slds,slds:it_it|0,slds_judge_deepseek_v4_pro_stderr,4.234299579540037 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,71.81219110378913 | |
| Mistral-Medium-3.5-128B,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.631047597183439 | |
| Mistral-Medium-3.5-128B,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,63.050713153724246 | |
| Mistral-Medium-3.5-128B,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.29796511259066905 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,62.2 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,1.0684135611683516 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,55.3 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,1.1472273764456302 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score,0.5717948717948718 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score_stderr,0.02508830145469484 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score,0.14871794871794872 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score_stderr,0.05000654884107343 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq,0.005128205128205128 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq_stderr,0.0036215247113446127 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail,0.01282051282051282 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail_stderr,0.00570395327472415 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,68.81669307976756 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.3033078699843879 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,71.4168039538715 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.7318693303340331 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,33.97034596375618 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.8241710280040172 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,55.65 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,1.0599551995842234 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,70.02471169686986 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.7126590548938568 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score,0.6344463971880492 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score_stderr,0.02020686007672834 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score,0.34797891036906853 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score_stderr,0.03752521598086929 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq,0.07908611599297012 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq_stderr,0.01132362467553828 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail,0.015817223198594025 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail_stderr,0.005235146433925954 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,72.57825370675452 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.7266859742907205 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,71.54036243822075 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.714334282229442 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro,47.00934579439252 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro_stderr,2.530766262348898 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,58.2 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,1.1835556683572177 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,64.57990115321252 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.7118183518062515 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,47.48764415156507 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,0.7333867806888711 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,71.23613312202852 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.32558003818975667 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro,57.5 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro_stderr,3.046358979224712 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,64.40691927512356 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.7451837195006401 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,44.77759472817134 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.8704263241042118 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,63.5172981878089 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.7300661323256884 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,69.31590068674062 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.32062473415486825 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score,0.4874517374517375 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score_stderr,0.015536851660606569 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score,0.07239382239382239 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score_stderr,0.029443613301367053 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq,0.09749034749034749 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq_stderr,0.009220119757600878 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail,0.016409266409266408 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail_stderr,0.003948949886117705 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:it_de|0,slds_judge_deepseek_v4_pro,65.83333333333333 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:it_de|0,slds_judge_deepseek_v4_pro_stderr,3.7856053783784818 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:de_de|0,slds_judge_deepseek_v4_pro,58.59903381642512 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:de_de|0,slds_judge_deepseek_v4_pro_stderr,1.8997290580600898 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro,53.71980676328502 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro_stderr,1.6453237976020827 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,71.17792421746293 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.7465005502403311 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,68.10089804543054 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.3230010633512132 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,71.29324546952225 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.7291300073912078 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,53.9 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,1.281468222009464 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,71.78747940691927 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.6897661599989419 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,68.94563426688633 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.75077964724676 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,68.18541996830427 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.3055697093548537 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,67.54530477759472 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.7826795540096859 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:de_it|0,slds_judge_deepseek_v4_pro,44.009661835748794 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:de_it|0,slds_judge_deepseek_v4_pro_stderr,1.8259472374680938 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,71.67215815485997 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.72616034636876 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,64.00329489291597 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.8046093444458703 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,69.43986820428336 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.7154739530387664 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score,0.2617554858934169 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score_stderr,0.01741719821212992 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score,-0.45454545454545453 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score_stderr,0.034800279146924226 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq,0.0219435736677116 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq_stderr,0.0058045147321163365 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail,0.0219435736677116 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail_stderr,0.005804514732116337 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro,60.5607476635514 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro_stderr,2.7013576910662174 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,70.56836902800659 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.6957880204534792 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1,69.90825688073394 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1_stderr,1.2429201172987845 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1,62.99762470308789 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1_stderr,0.5575099166667592 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score,0.3389261744966443 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score_stderr,0.015839877057395618 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score,-0.20469798657718122 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score_stderr,0.030681856821760972 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq,0.1174496644295302 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq_stderr,0.010773824650415336 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail,0.02796420581655481 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail_stderr,0.005517173535257447 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro,58.13084112149533 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro_stderr,1.8310342210042705 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,42.43822075782537 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,0.8337229567786303 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,71.72741679873216 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.34593658558065227 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:it_it|0,slds_judge_deepseek_v4_pro,50.833333333333336 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,slds,slds:it_it|0,slds_judge_deepseek_v4_pro_stderr,6.5664820770856345 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score,0.7738287560581584 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score_stderr,0.016828557383731502 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score,0.5993537964458805 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score_stderr,0.03087396716447467 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq,0.051696284329563816 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq_stderr,0.008906542676774426 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail,0.01615508885298869 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail_stderr,0.005071352046657155 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,56.9 | |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,1.0109699805174928 | |
| Olmo-3.1-32B-Think,slds,slds:de_it|0,slds_judge_deepseek_v4_pro,17.82608695652174 | |
| Olmo-3.1-32B-Think,slds,slds:de_it|0,slds_judge_deepseek_v4_pro_stderr,1.147220179109651 | |
| Olmo-3.1-32B-Think,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,29.35 | |
| Olmo-3.1-32B-Think,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,1.5055633847592205 | |
| Olmo-3.1-32B-Think,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score,0.2799227799227799 | |
| Olmo-3.1-32B-Think,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score_stderr,0.013955277678191937 | |
| Olmo-3.1-32B-Think,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score,-0.06853281853281853 | |
| Olmo-3.1-32B-Think,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score_stderr,0.02454772795968946 | |
| Olmo-3.1-32B-Think,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq,0.3716216216216216 | |
| Olmo-3.1-32B-Think,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq_stderr,0.015020726162835034 | |
| Olmo-3.1-32B-Think,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail,0.0019305019305019305 | |
| Olmo-3.1-32B-Think,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail_stderr,0.0013644113921937489 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,58.73970345963756 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.892871742503893 | |
| Olmo-3.1-32B-Think,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro,30.0 | |
| Olmo-3.1-32B-Think,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro_stderr,4.92365963917331 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,53.056013179571664 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.8831561837028448 | |
| Olmo-3.1-32B-Think,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,29.587955625990492 | |
| Olmo-3.1-32B-Think,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.4516354070435581 | |
| Olmo-3.1-32B-Think,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,27.7 | |
| Olmo-3.1-32B-Think,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,1.4779960628530238 | |
| Olmo-3.1-32B-Think,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score,0.2080536912751678 | |
| Olmo-3.1-32B-Think,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score_stderr,0.013583442626021111 | |
| Olmo-3.1-32B-Think,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score,-0.39932885906040266 | |
| Olmo-3.1-32B-Think,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score_stderr,0.027102986863086247 | |
| Olmo-3.1-32B-Think,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq,0.18456375838926176 | |
| Olmo-3.1-32B-Think,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq_stderr,0.012982026401698345 | |
| Olmo-3.1-32B-Think,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail,0.0 | |
| Olmo-3.1-32B-Think,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail_stderr,0.0 | |
| Olmo-3.1-32B-Think,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,30.00528262017961 | |
| Olmo-3.1-32B-Think,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.492228329076648 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,52.09225700164745 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.8204642637707752 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,13.665568369028007 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.6125775375369794 | |
| Olmo-3.1-32B-Think,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro,25.42056074766355 | |
| Olmo-3.1-32B-Think,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro_stderr,1.6170074189619172 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,6.9851729818780885 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.48582373929476563 | |
| Olmo-3.1-32B-Think,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,26.45 | |
| Olmo-3.1-32B-Think,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,1.388932383461896 | |
| Olmo-3.1-32B-Think,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,27.4 | |
| Olmo-3.1-32B-Think,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,1.2626047894219945 | |
| Olmo-3.1-32B-Think,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score,0.28974358974358977 | |
| Olmo-3.1-32B-Think,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score_stderr,0.02300062824368798 | |
| Olmo-3.1-32B-Think,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score,-0.3923076923076923 | |
| Olmo-3.1-32B-Think,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score_stderr,0.04585350391141277 | |
| Olmo-3.1-32B-Think,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq,0.028205128205128206 | |
| Olmo-3.1-32B-Think,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq_stderr,0.008394146410081477 | |
| Olmo-3.1-32B-Think,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail,0.0 | |
| Olmo-3.1-32B-Think,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail_stderr,0.0 | |
| Olmo-3.1-32B-Think,slds,slds:de_de|0,slds_judge_deepseek_v4_pro,32.85024154589372 | |
| Olmo-3.1-32B-Think,slds,slds:de_de|0,slds_judge_deepseek_v4_pro_stderr,1.4641916442358907 | |
| Olmo-3.1-32B-Think,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,41.344426835710514 | |
| Olmo-3.1-32B-Think,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.5222912468274296 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,18.83855024711697 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.8778733222094166 | |
| Olmo-3.1-32B-Think,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro,36.074766355140184 | |
| Olmo-3.1-32B-Think,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro_stderr,1.8195678551336376 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,61.30971993410214 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.7091812656104654 | |
| Olmo-3.1-32B-Think,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,41.15161119915478 | |
| Olmo-3.1-32B-Think,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.49080708602388434 | |
| Olmo-3.1-32B-Think,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1,28.294536817102138 | |
| Olmo-3.1-32B-Think,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1_stderr,0.4845306632163342 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,49.01153212520593 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.8427280476271602 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,10.939044481054365 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,0.6631168016673902 | |
| Olmo-3.1-32B-Think,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1,38.89908256880734 | |
| Olmo-3.1-32B-Think,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1_stderr,1.25531992397608 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,9.925864909390445 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.5582337989206269 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,65.63426688632619 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.7629866604421818 | |
| Olmo-3.1-32B-Think,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,27.6 | |
| Olmo-3.1-32B-Think,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,1.3768363708007563 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,69.68698517298188 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.7138880672985701 | |
| Olmo-3.1-32B-Think,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score,0.31985940246045697 | |
| Olmo-3.1-32B-Think,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score_stderr,0.0195706271138779 | |
| Olmo-3.1-32B-Think,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score,-0.20210896309314588 | |
| Olmo-3.1-32B-Think,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score_stderr,0.037552304721273216 | |
| Olmo-3.1-32B-Think,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq,0.15817223198594024 | |
| Olmo-3.1-32B-Think,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq_stderr,0.01531096547439023 | |
| Olmo-3.1-32B-Think,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail,0.0017574692442882249 | |
| Olmo-3.1-32B-Think,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail_stderr,0.0017574692442882086 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,58.94563426688632 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.7440562509751292 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,59.91762767710049 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.7822919530000187 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,63.55848434925865 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.7119574314231909 | |
| Olmo-3.1-32B-Think,slds,slds:it_it|0,slds_judge_deepseek_v4_pro,24.166666666666668 | |
| Olmo-3.1-32B-Think,slds,slds:it_it|0,slds_judge_deepseek_v4_pro_stderr,6.210735248199871 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,65.93080724876441 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.7232520849332197 | |
| Olmo-3.1-32B-Think,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro,24.485981308411215 | |
| Olmo-3.1-32B-Think,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro_stderr,1.9840380713563195 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,69.11861614497529 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.7383330088941008 | |
| Olmo-3.1-32B-Think,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,35.50977284733228 | |
| Olmo-3.1-32B-Think,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.4651320243378906 | |
| Olmo-3.1-32B-Think,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,25.35 | |
| Olmo-3.1-32B-Think,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,1.468047450385344 | |
| Olmo-3.1-32B-Think,slds,slds:it_de|0,slds_judge_deepseek_v4_pro,25.0 | |
| Olmo-3.1-32B-Think,slds,slds:it_de|0,slds_judge_deepseek_v4_pro_stderr,5.838742081211422 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,12.742998352553542 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,0.7036770810990514 | |
| Olmo-3.1-32B-Think,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,33.48388800845219 | |
| Olmo-3.1-32B-Think,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.43855895419371793 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,12.355848434925864 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.6387747262838742 | |
| Olmo-3.1-32B-Think,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score,0.37318255250403876 | |
| Olmo-3.1-32B-Think,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score_stderr,0.019455256733856664 | |
| Olmo-3.1-32B-Think,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score,0.1098546042003231 | |
| Olmo-3.1-32B-Think,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score_stderr,0.03178717828730386 | |
| Olmo-3.1-32B-Think,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq,0.36348949919224555 | |
| Olmo-3.1-32B-Think,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq_stderr,0.019348819953866607 | |
| Olmo-3.1-32B-Think,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail,0.0 | |
| Olmo-3.1-32B-Think,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail_stderr,0.0 | |
| Olmo-3.1-32B-Think,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score,0.1896551724137931 | |
| Olmo-3.1-32B-Think,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score_stderr,0.015532721727214465 | |
| Olmo-3.1-32B-Think,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score,-0.5815047021943573 | |
| Olmo-3.1-32B-Think,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score_stderr,0.03126499209227933 | |
| Olmo-3.1-32B-Think,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq,0.03918495297805643 | |
| Olmo-3.1-32B-Think,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq_stderr,0.007687937547442818 | |
| Olmo-3.1-32B-Think,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail,0.003134796238244514 | |
| Olmo-3.1-32B-Think,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail_stderr,0.0022148950918982426 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,7.28171334431631 | |
| Olmo-3.1-32B-Think,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.49964957687145 | |
| Olmo-3.1-32B-Think,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro,25.02415458937198 | |
| Olmo-3.1-32B-Think,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro_stderr,1.3881958901882363 | |
| Qwen3.5-35B-A3B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score,0.541025641025641 | |
| Qwen3.5-35B-A3B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score_stderr,0.025265525491284295 | |
| Qwen3.5-35B-A3B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score,0.08461538461538462 | |
| Qwen3.5-35B-A3B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score_stderr,0.050454900682540875 | |
| Qwen3.5-35B-A3B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq,0.002564102564102564 | |
| Qwen3.5-35B-A3B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq_stderr,0.0025641025641025598 | |
| Qwen3.5-35B-A3B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail,0.0 | |
| Qwen3.5-35B-A3B,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail_stderr,0.0 | |
| Qwen3.5-35B-A3B,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro,46.666666666666664 | |
| Qwen3.5-35B-A3B,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro_stderr,3.760507165451775 | |
| Qwen3.5-35B-A3B,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro,52.52336448598131 | |
| Qwen3.5-35B-A3B,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro_stderr,1.7571350274141644 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,62.57001647446458 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.8129375593238273 | |
| Qwen3.5-35B-A3B,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro,45.21739130434783 | |
| Qwen3.5-35B-A3B,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro_stderr,1.4148867918406296 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,44.85996705107084 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,0.9371611853793765 | |
| Qwen3.5-35B-A3B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score,0.5135135135135135 | |
| Qwen3.5-35B-A3B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score_stderr,0.015536069453385079 | |
| Qwen3.5-35B-A3B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score,0.03571428571428571 | |
| Qwen3.5-35B-A3B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score_stderr,0.030928267187414486 | |
| Qwen3.5-35B-A3B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq,0.008687258687258687 | |
| Qwen3.5-35B-A3B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq_stderr,0.002884539870499554 | |
| Qwen3.5-35B-A3B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail,0.0019305019305019305 | |
| Qwen3.5-35B-A3B,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail_stderr,0.0013644113921937693 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,65.60131795716639 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.6965699375462309 | |
| Qwen3.5-35B-A3B,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,53.65 | |
| Qwen3.5-35B-A3B,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,1.163035147262905 | |
| Qwen3.5-35B-A3B,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,67.40887480190175 | |
| Qwen3.5-35B-A3B,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.26234760286197556 | |
| Qwen3.5-35B-A3B,slds,slds:it_it|0,slds_judge_deepseek_v4_pro,45.0 | |
| Qwen3.5-35B-A3B,slds,slds:it_it|0,slds_judge_deepseek_v4_pro_stderr,4.17423554968361 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,69.75288303130148 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.6716620907704631 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,71.09555189456343 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.6443743062666116 | |
| Qwen3.5-35B-A3B,slds,slds:de_it|0,slds_judge_deepseek_v4_pro,43.23671497584541 | |
| Qwen3.5-35B-A3B,slds,slds:de_it|0,slds_judge_deepseek_v4_pro_stderr,1.287915432474847 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,35.93080724876442 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,0.9177477126753915 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,71.03789126853377 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.7612181917021642 | |
| Qwen3.5-35B-A3B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score,0.3366890380313199 | |
| Qwen3.5-35B-A3B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score_stderr,0.015814204343422646 | |
| Qwen3.5-35B-A3B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score,-0.30089485458612975 | |
| Qwen3.5-35B-A3B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score_stderr,0.031458307379319435 | |
| Qwen3.5-35B-A3B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq,0.025727069351230425 | |
| Qwen3.5-35B-A3B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq_stderr,0.00529797308046057 | |
| Qwen3.5-35B-A3B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail,0.0011185682326621924 | |
| Qwen3.5-35B-A3B,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail_stderr,0.0011185682326621974 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,71.49917627677101 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.7753512608960605 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,66.4003294892916 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.6545825428187798 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,69.9011532125206 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.6781330756206071 | |
| Qwen3.5-35B-A3B,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,66.96513470681458 | |
| Qwen3.5-35B-A3B,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.28390515107214676 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,71.91927512355848 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.6788536726905773 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,64.83525535420098 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.666786935460694 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,28.17957166392092 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.9106831880805918 | |
| Qwen3.5-35B-A3B,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,55.5 | |
| Qwen3.5-35B-A3B,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,0.9841712070692378 | |
| Qwen3.5-35B-A3B,slds,slds:it_de|0,slds_judge_deepseek_v4_pro,43.333333333333336 | |
| Qwen3.5-35B-A3B,slds,slds:it_de|0,slds_judge_deepseek_v4_pro_stderr,6.890192121758832 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,73.64909390444811 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.6422058203636338 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,72.71004942339374 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.6909282612518393 | |
| Qwen3.5-35B-A3B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score,0.2617554858934169 | |
| Qwen3.5-35B-A3B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score_stderr,0.01741719821212991 | |
| Qwen3.5-35B-A3B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score,-0.47492163009404387 | |
| Qwen3.5-35B-A3B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score_stderr,0.034832680281879275 | |
| Qwen3.5-35B-A3B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq,0.001567398119122257 | |
| Qwen3.5-35B-A3B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq_stderr,0.0015673981191222583 | |
| Qwen3.5-35B-A3B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail,0.001567398119122257 | |
| Qwen3.5-35B-A3B,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail_stderr,0.0015673981191222574 | |
| Qwen3.5-35B-A3B,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,66.41310089804543 | |
| Qwen3.5-35B-A3B,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.2712933503416803 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,71.69686985172982 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.7287736038776512 | |
| Qwen3.5-35B-A3B,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1,32.018348623853214 | |
| Qwen3.5-35B-A3B,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1_stderr,1.462065318415259 | |
| Qwen3.5-35B-A3B,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,70.03961965134707 | |
| Qwen3.5-35B-A3B,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.32429998748148775 | |
| Qwen3.5-35B-A3B,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro,46.44859813084112 | |
| Qwen3.5-35B-A3B,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro_stderr,1.732673433991262 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,70.98846787479407 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.6499205656137991 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,51.42504118616145 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.8453110800918143 | |
| Qwen3.5-35B-A3B,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,55.65 | |
| Qwen3.5-35B-A3B,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,1.1243702871890426 | |
| Qwen3.5-35B-A3B,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,68.44162704701532 | |
| Qwen3.5-35B-A3B,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.25083322005870534 | |
| Qwen3.5-35B-A3B,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,63.787638668779714 | |
| Qwen3.5-35B-A3B,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.32857451661871173 | |
| Qwen3.5-35B-A3B,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro,48.598130841121495 | |
| Qwen3.5-35B-A3B,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro_stderr,1.8706571318482172 | |
| Qwen3.5-35B-A3B,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,55.1 | |
| Qwen3.5-35B-A3B,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,1.0632981778764488 | |
| Qwen3.5-35B-A3B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score,0.6133567662565905 | |
| Qwen3.5-35B-A3B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score_stderr,0.020433258046826084 | |
| Qwen3.5-35B-A3B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score,0.2513181019332162 | |
| Qwen3.5-35B-A3B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score_stderr,0.04007551503496933 | |
| Qwen3.5-35B-A3B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq,0.02460456942003515 | |
| Qwen3.5-35B-A3B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq_stderr,0.006500160423763841 | |
| Qwen3.5-35B-A3B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail,0.0 | |
| Qwen3.5-35B-A3B,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail_stderr,0.0 | |
| Qwen3.5-35B-A3B,slds,slds:de_de|0,slds_judge_deepseek_v4_pro,49.42028985507246 | |
| Qwen3.5-35B-A3B,slds,slds:de_de|0,slds_judge_deepseek_v4_pro_stderr,1.212887068955132 | |
| Qwen3.5-35B-A3B,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1,48.17102137767221 | |
| Qwen3.5-35B-A3B,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1_stderr,0.5537048517621974 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,70.00823723228996 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.6790896244386568 | |
| Qwen3.5-35B-A3B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score,0.7722132471728594 | |
| Qwen3.5-35B-A3B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score_stderr,0.016870914251330294 | |
| Qwen3.5-35B-A3B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score,0.5573505654281099 | |
| Qwen3.5-35B-A3B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score_stderr,0.03308409105784684 | |
| Qwen3.5-35B-A3B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq,0.012924071082390954 | |
| Qwen3.5-35B-A3B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq_stderr,0.0045433972628177825 | |
| Qwen3.5-35B-A3B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail,0.0032310177705977385 | |
| Qwen3.5-35B-A3B,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail_stderr,0.0022828253851532704 | |
| Qwen3.5-35B-A3B,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,59.15 | |
| Qwen3.5-35B-A3B,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,1.1643306356640002 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,72.0675453047776 | |
| Qwen3.5-35B-A3B,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.6538253154798236 | |
| Qwen3.5-35B-A3B,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,59.0 | |
| Qwen3.5-35B-A3B,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,1.258139329670733 | |
| gemma-4-31B-it,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,57.65 | |
| gemma-4-31B-it,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.9323270179189838 | |
| gemma-4-31B-it,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro,45.265700483091784 | |
| gemma-4-31B-it,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro_stderr,1.4048665681908326 | |
| gemma-4-31B-it,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score,0.30407523510971785 | |
| gemma-4-31B-it,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score_stderr,0.018226444401320468 | |
| gemma-4-31B-it,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score,-0.39184952978056425 | |
| gemma-4-31B-it,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score_stderr,0.036452888802640936 | |
| gemma-4-31B-it,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq,0.0 | |
| gemma-4-31B-it,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq_stderr,0.0 | |
| gemma-4-31B-it,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail,0.0 | |
| gemma-4-31B-it,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail_stderr,0.0 | |
| gemma-4-31B-it,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,60.51769677760169 | |
| gemma-4-31B-it,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.3431905771758002 | |
| gemma-4-31B-it,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1,60.73394495412844 | |
| gemma-4-31B-it,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1_stderr,1.1087763014768337 | |
| gemma-4-31B-it,slds,slds:de_de|0,slds_judge_deepseek_v4_pro,52.17391304347826 | |
| gemma-4-31B-it,slds,slds:de_de|0,slds_judge_deepseek_v4_pro_stderr,1.2805228365107884 | |
| gemma-4-31B-it,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score,0.5202702702702703 | |
| gemma-4-31B-it,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score_stderr,0.015528969846263289 | |
| gemma-4-31B-it,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score,0.05115830115830116 | |
| gemma-4-31B-it,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score_stderr,0.030877114511954826 | |
| gemma-4-31B-it,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq,0.010617760617760617 | |
| gemma-4-31B-it,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq_stderr,0.0031858721611624724 | |
| gemma-4-31B-it,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail,0.0 | |
| gemma-4-31B-it,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail_stderr,0.0 | |
| gemma-4-31B-it,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,65.41186161449752 | |
| gemma-4-31B-it,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.738235118326801 | |
| gemma-4-31B-it,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,46.4827018121911 | |
| gemma-4-31B-it,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.7889001188883009 | |
| gemma-4-31B-it,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,17.28995057660626 | |
| gemma-4-31B-it,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,0.7668583918922728 | |
| gemma-4-31B-it,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,59.489291598023065 | |
| gemma-4-31B-it,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.7674335181532338 | |
| gemma-4-31B-it,slds,slds:it_it|0,slds_judge_deepseek_v4_pro,45.0 | |
| gemma-4-31B-it,slds,slds:it_it|0,slds_judge_deepseek_v4_pro_stderr,3.3709993123162105 | |
| gemma-4-31B-it,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,62.46293245469522 | |
| gemma-4-31B-it,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.7330619398693714 | |
| gemma-4-31B-it,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro,50.2803738317757 | |
| gemma-4-31B-it,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro_stderr,1.7438606516093076 | |
| gemma-4-31B-it,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,46.20263591433278 | |
| gemma-4-31B-it,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.7503018020663484 | |
| gemma-4-31B-it,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,26.29324546952224 | |
| gemma-4-31B-it,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,0.8107368241019507 | |
| gemma-4-31B-it,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score,0.8077544426494345 | |
| gemma-4-31B-it,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score_stderr,0.015851617939816997 | |
| gemma-4-31B-it,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score,0.6219709208400647 | |
| gemma-4-31B-it,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score_stderr,0.03133208024644801 | |
| gemma-4-31B-it,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq,0.006462035541195477 | |
| gemma-4-31B-it,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq_stderr,0.003223165953959457 | |
| gemma-4-31B-it,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail,0.0 | |
| gemma-4-31B-it,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail_stderr,0.0 | |
| gemma-4-31B-it,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,68.83254094030639 | |
| gemma-4-31B-it,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.3172895090216997 | |
| gemma-4-31B-it,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,65.0329489291598 | |
| gemma-4-31B-it,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.7344561061796775 | |
| gemma-4-31B-it,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro,44.953271028037385 | |
| gemma-4-31B-it,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro_stderr,1.8177102049758953 | |
| gemma-4-31B-it,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,55.782537067545306 | |
| gemma-4-31B-it,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.7560776786578439 | |
| gemma-4-31B-it,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score,0.7152899824253075 | |
| gemma-4-31B-it,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score_stderr,0.01893512941130128 | |
| gemma-4-31B-it,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score,0.43409490333919154 | |
| gemma-4-31B-it,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score_stderr,0.037717600507447074 | |
| gemma-4-31B-it,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq,0.0035149384885764497 | |
| gemma-4-31B-it,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq_stderr,0.0024832479923571275 | |
| gemma-4-31B-it,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail,0.0 | |
| gemma-4-31B-it,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail_stderr,0.0 | |
| gemma-4-31B-it,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,13.245469522240526 | |
| gemma-4-31B-it,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.693199293946543 | |
| gemma-4-31B-it,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,49.29159802306425 | |
| gemma-4-31B-it,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.8019238504115288 | |
| gemma-4-31B-it,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,57.90774299835255 | |
| gemma-4-31B-it,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.7311835778504409 | |
| gemma-4-31B-it,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,67.69677760169044 | |
| gemma-4-31B-it,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.3368209372479 | |
| gemma-4-31B-it,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,57.7 | |
| gemma-4-31B-it,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,1.0167195252206118 | |
| gemma-4-31B-it,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,43.327841845140036 | |
| gemma-4-31B-it,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.7586550172079352 | |
| gemma-4-31B-it,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,20.58484349258649 | |
| gemma-4-31B-it,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.8120613217730381 | |
| gemma-4-31B-it,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,56.779242174629324 | |
| gemma-4-31B-it,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.7872739984105398 | |
| gemma-4-31B-it,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,55.799011532125206 | |
| gemma-4-31B-it,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.7660570169698938 | |
| gemma-4-31B-it,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,58.37726523887974 | |
| gemma-4-31B-it,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.747540342302703 | |
| gemma-4-31B-it,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,52.25 | |
| gemma-4-31B-it,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,1.2060098668729764 | |
| gemma-4-31B-it,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,63.65 | |
| gemma-4-31B-it,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.9382371473799221 | |
| gemma-4-31B-it,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,59.61701003697834 | |
| gemma-4-31B-it,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.3244345138876875 | |
| gemma-4-31B-it,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score,0.39373601789709173 | |
| gemma-4-31B-it,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score_stderr,0.016349622393687247 | |
| gemma-4-31B-it,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score,-0.20917225950782997 | |
| gemma-4-31B-it,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score_stderr,0.032665998862668695 | |
| gemma-4-31B-it,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq,0.003355704697986577 | |
| gemma-4-31B-it,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq_stderr,0.0019352462346596076 | |
| gemma-4-31B-it,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail,0.0 | |
| gemma-4-31B-it,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail_stderr,0.0 | |
| gemma-4-31B-it,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,63.394083465398836 | |
| gemma-4-31B-it,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.32196676119374035 | |
| gemma-4-31B-it,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,60.19769357495881 | |
| gemma-4-31B-it,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.7740719489319944 | |
| gemma-4-31B-it,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro,52.80373831775701 | |
| gemma-4-31B-it,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro_stderr,1.7953602721593938 | |
| gemma-4-31B-it,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,59.91762767710049 | |
| gemma-4-31B-it,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.7483069042464531 | |
| gemma-4-31B-it,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,58.62438220757825 | |
| gemma-4-31B-it,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.730029660506644 | |
| gemma-4-31B-it,slds,slds:de_it|0,slds_judge_deepseek_v4_pro,41.88405797101449 | |
| gemma-4-31B-it,slds,slds:de_it|0,slds_judge_deepseek_v4_pro_stderr,1.3813400751278693 | |
| gemma-4-31B-it,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1,54.912114014251785 | |
| gemma-4-31B-it,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1_stderr,0.5034603714784261 | |
| gemma-4-31B-it,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,59.45 | |
| gemma-4-31B-it,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.9489414891070707 | |
| gemma-4-31B-it,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,64.25 | |
| gemma-4-31B-it,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.9006906897448006 | |
| gemma-4-31B-it,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,60.739566825145275 | |
| gemma-4-31B-it,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.34137033970645814 | |
| gemma-4-31B-it,slds,slds:it_de|0,slds_judge_deepseek_v4_pro,50.833333333333336 | |
| gemma-4-31B-it,slds,slds:it_de|0,slds_judge_deepseek_v4_pro_stderr,5.567537583840342 | |
| gemma-4-31B-it,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score,0.6205128205128205 | |
| gemma-4-31B-it,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score_stderr,0.024603626924097413 | |
| gemma-4-31B-it,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score,0.24102564102564103 | |
| gemma-4-31B-it,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score_stderr,0.049207253848194826 | |
| gemma-4-31B-it,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq,0.0 | |
| gemma-4-31B-it,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq_stderr,0.0 | |
| gemma-4-31B-it,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail,0.0 | |
| gemma-4-31B-it,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail_stderr,0.0 | |
| gemma-4-31B-it,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro,49.166666666666664 | |
| gemma-4-31B-it,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro_stderr,3.1281549730397846 | |
| gpt-oss-120b,slds,slds:it_de|0,slds_judge_deepseek_v4_pro,39.166666666666664 | |
| gpt-oss-120b,slds,slds:it_de|0,slds_judge_deepseek_v4_pro_stderr,6.68085611159516 | |
| gpt-oss-120b,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini,54.53871499176277 | |
| gpt-oss-120b,slt,slt-paragraph_level:rm-de|0,slt_judge_gpt-4o-mini_stderr,0.7954197403881214 | |
| gpt-oss-120b,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro,45.046728971962615 | |
| gpt-oss-120b,slds,slds:fr_de|0,slds_judge_deepseek_v4_pro_stderr,2.2705936874422665 | |
| gpt-oss-120b,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini,69.46645536185949 | |
| gpt-oss-120b,sdst,sdst-text_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.33001947020132855 | |
| gpt-oss-120b,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini,48.9 | |
| gpt-oss-120b,sscprt,sscprt-press_release:de-fr|0,slt_judge_gpt-4o-mini_stderr,1.175097558229435 | |
| gpt-oss-120b,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini,53.66556836902801 | |
| gpt-oss-120b,slt,slt-paragraph_level:rm-fr|0,slt_judge_gpt-4o-mini_stderr,0.7805523538477475 | |
| gpt-oss-120b,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score,0.30089485458612975 | |
| gpt-oss-120b,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,trad_score_stderr,0.015348039224239775 | |
| gpt-oss-120b,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score,-0.38478747203579416 | |
| gpt-oss-120b,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_score_stderr,0.030642901926725016 | |
| gpt-oss-120b,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq,0.013422818791946308 | |
| gpt-oss-120b,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,idk_freq_stderr,0.0038508949131700427 | |
| gpt-oss-120b,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail,0.0 | |
| gpt-oss-120b,lexam_mcq_8_idk,lexam_mcq_8_idk:de|0,extract_fail_stderr,0.0 | |
| gpt-oss-120b,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini,69.09390444810543 | |
| gpt-oss-120b,slt,slt-paragraph_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.6543925915519545 | |
| gpt-oss-120b,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini,36.4497528830313 | |
| gpt-oss-120b,slt,slt-paragraph_level:en-rm|0,slt_judge_gpt-4o-mini_stderr,0.9121441410373098 | |
| gpt-oss-120b,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini,72.84184514003294 | |
| gpt-oss-120b,slt,slt-paragraph_level:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.6504854854028201 | |
| gpt-oss-120b,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini,72.15815485996706 | |
| gpt-oss-120b,slt,slt-paragraph_level:en-it|0,slt_judge_gpt-4o-mini_stderr,0.6182917959472572 | |
| gpt-oss-120b,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini,48.35 | |
| gpt-oss-120b,sscprt,sscprt-press_release:it-de|0,slt_judge_gpt-4o-mini_stderr,1.2596910764311258 | |
| gpt-oss-120b,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini,69.1845140032949 | |
| gpt-oss-120b,slt,slt-paragraph_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.6156209844003546 | |
| gpt-oss-120b,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro,50.0 | |
| gpt-oss-120b,slds,slds:it_fr|0,slds_judge_deepseek_v4_pro_stderr,5.365433699886599 | |
| gpt-oss-120b,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro,44.11214953271028 | |
| gpt-oss-120b,slds,slds:fr_it|0,slds_judge_deepseek_v4_pro_stderr,1.844574706002522 | |
| gpt-oss-120b,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score,0.24921630094043887 | |
| gpt-oss-120b,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,trad_score_stderr,0.017138622933403472 | |
| gpt-oss-120b,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score,-0.49686520376175547 | |
| gpt-oss-120b,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_score_stderr,0.03427707709277729 | |
| gpt-oss-120b,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq,0.004702194357366771 | |
| gpt-oss-120b,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,idk_freq_stderr,0.0027105479543554916 | |
| gpt-oss-120b,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail,0.0 | |
| gpt-oss-120b,lexam_mcq_16_idk,lexam_mcq_16_idk:de|0,extract_fail_stderr,0.0 | |
| gpt-oss-120b,slds,slds:de_de|0,slds_judge_deepseek_v4_pro,50.628019323671495 | |
| gpt-oss-120b,slds,slds:de_de|0,slds_judge_deepseek_v4_pro_stderr,1.4911709382345757 | |
| gpt-oss-120b,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1,60.96330275229358 | |
| gpt-oss-120b,lexam_oq,lexam_oq:en|0,lexam_oq_judge_deepseek_r1_stderr,1.1342347732028741 | |
| gpt-oss-120b,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1,50.25653206650831 | |
| gpt-oss-120b,lexam_oq,lexam_oq:de|0,lexam_oq_judge_deepseek_r1_stderr,0.5281174653405342 | |
| gpt-oss-120b,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini,58.2 | |
| gpt-oss-120b,sscprt,sscprt-press_release:it-fr|0,slt_judge_gpt-4o-mini_stderr,0.9765079821465784 | |
| gpt-oss-120b,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score,0.4527027027027027 | |
| gpt-oss-120b,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,trad_score_stderr,0.015472055709961265 | |
| gpt-oss-120b,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score,-0.07818532818532818 | |
| gpt-oss-120b,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_score_stderr,0.030731465692683403 | |
| gpt-oss-120b,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq,0.016409266409266408 | |
| gpt-oss-120b,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,idk_freq_stderr,0.003948949886117685 | |
| gpt-oss-120b,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail,0.0 | |
| gpt-oss-120b,lexam_mcq_4_idk,lexam_mcq_4_idk:de|0,extract_fail_stderr,0.0 | |
| gpt-oss-120b,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini,70.7660626029654 | |
| gpt-oss-120b,slt,slt-paragraph_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.6231284900878136 | |
| gpt-oss-120b,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro,52.61682242990654 | |
| gpt-oss-120b,slds,slds:fr_fr|0,slds_judge_deepseek_v4_pro_stderr,1.722896769411478 | |
| gpt-oss-120b,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini,70.59308072487644 | |
| gpt-oss-120b,slt,slt-paragraph_level:fr-en|0,slt_judge_gpt-4o-mini_stderr,0.7095428590691281 | |
| gpt-oss-120b,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini,25.7495881383855 | |
| gpt-oss-120b,slt,slt-paragraph_level:fr-rm|0,slt_judge_gpt-4o-mini_stderr,0.8551483593081269 | |
| gpt-oss-120b,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini,67.85831960461284 | |
| gpt-oss-120b,slt,slt-paragraph_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.6710075086474476 | |
| gpt-oss-120b,slds,slds:it_it|0,slds_judge_deepseek_v4_pro,50.833333333333336 | |
| gpt-oss-120b,slds,slds:it_it|0,slds_judge_deepseek_v4_pro_stderr,5.567537583840342 | |
| gpt-oss-120b,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini,55.42833607907743 | |
| gpt-oss-120b,slt,slt-paragraph_level:rm-it|0,slt_judge_gpt-4o-mini_stderr,0.7449122343952672 | |
| gpt-oss-120b,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini,60.62863180137348 | |
| gpt-oss-120b,sdst,sdst-text_level:fr-de|0,slt_judge_gpt-4o-mini_stderr,0.3261891436792929 | |
| gpt-oss-120b,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini,71.72158154859967 | |
| gpt-oss-120b,slt,slt-paragraph_level:de-en|0,slt_judge_gpt-4o-mini_stderr,0.6382640342907614 | |
| gpt-oss-120b,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini,53.26194398682043 | |
| gpt-oss-120b,slt,slt-paragraph_level:rm-en|0,slt_judge_gpt-4o-mini_stderr,0.7644187450820111 | |
| gpt-oss-120b,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini,59.80190174326466 | |
| gpt-oss-120b,sdst,sdst-text_level:it-de|0,slt_judge_gpt-4o-mini_stderr,0.3149175984753543 | |
| gpt-oss-120b,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score,0.4666666666666667 | |
| gpt-oss-120b,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,trad_score_stderr,0.02529460802398647 | |
| gpt-oss-120b,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score,-0.06666666666666667 | |
| gpt-oss-120b,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_score_stderr,0.05058921604797294 | |
| gpt-oss-120b,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq,0.0 | |
| gpt-oss-120b,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,idk_freq_stderr,0.0 | |
| gpt-oss-120b,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail,0.0 | |
| gpt-oss-120b,lexam_mcq_16_idk,lexam_mcq_16_idk:en|0,extract_fail_stderr,0.0 | |
| gpt-oss-120b,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini,50.0 | |
| gpt-oss-120b,sscprt,sscprt-press_release:de-it|0,slt_judge_gpt-4o-mini_stderr,1.2092607484694708 | |
| gpt-oss-120b,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini,63.917062863180135 | |
| gpt-oss-120b,sdst,sdst-text_level:de-fr|0,slt_judge_gpt-4o-mini_stderr,0.3068659549553683 | |
| gpt-oss-120b,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score,0.5307557117750439 | |
| gpt-oss-120b,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,trad_score_stderr,0.020939806681564286 | |
| gpt-oss-120b,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score,0.0632688927943761 | |
| gpt-oss-120b,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_score_stderr,0.04183804240381706 | |
| gpt-oss-120b,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq,0.0017574692442882249 | |
| gpt-oss-120b,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,idk_freq_stderr,0.0017574692442882134 | |
| gpt-oss-120b,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail,0.0 | |
| gpt-oss-120b,lexam_mcq_8_idk,lexam_mcq_8_idk:en|0,extract_fail_stderr,0.0 | |
| gpt-oss-120b,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini,73.25370675453048 | |
| gpt-oss-120b,slt,slt-paragraph_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.6259882377622925 | |
| gpt-oss-120b,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini,71.85337726523888 | |
| gpt-oss-120b,slt,slt-paragraph_level:en-fr|0,slt_judge_gpt-4o-mini_stderr,0.6047350868083297 | |
| gpt-oss-120b,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini,70.32948929159802 | |
| gpt-oss-120b,slt,slt-paragraph_level:en-de|0,slt_judge_gpt-4o-mini_stderr,0.6196755361444402 | |
| gpt-oss-120b,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini,70.98846787479407 | |
| gpt-oss-120b,slt,slt-paragraph_level:it-en|0,slt_judge_gpt-4o-mini_stderr,0.6700870476280398 | |
| gpt-oss-120b,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini,64.10459587955626 | |
| gpt-oss-120b,sdst,sdst-text_level:de-it|0,slt_judge_gpt-4o-mini_stderr,0.30430886240776395 | |
| gpt-oss-120b,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini,33.86326194398682 | |
| gpt-oss-120b,slt,slt-paragraph_level:de-rm|0,slt_judge_gpt-4o-mini_stderr,0.8896753176916867 | |
| gpt-oss-120b,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini,56.65 | |
| gpt-oss-120b,sscprt,sscprt-press_release:fr-it|0,slt_judge_gpt-4o-mini_stderr,1.0757199295514497 | |
| gpt-oss-120b,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini,64.87057580559957 | |
| gpt-oss-120b,sdst,sdst-text_level:fr-it|0,slt_judge_gpt-4o-mini_stderr,0.33076551529010334 | |
| gpt-oss-120b,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini,50.9 | |
| gpt-oss-120b,sscprt,sscprt-press_release:fr-de|0,slt_judge_gpt-4o-mini_stderr,1.0542805782563014 | |
| gpt-oss-120b,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro,43.6231884057971 | |
| gpt-oss-120b,slds,slds:de_fr|0,slds_judge_deepseek_v4_pro_stderr,1.405052030721485 | |
| gpt-oss-120b,slds,slds:de_it|0,slds_judge_deepseek_v4_pro,40.38647342995169 | |
| gpt-oss-120b,slds,slds:de_it|0,slds_judge_deepseek_v4_pro_stderr,1.2882584462166282 | |
| gpt-oss-120b,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score,0.7237479806138933 | |
| gpt-oss-120b,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,trad_score_stderr,0.01798672834945694 | |
| gpt-oss-120b,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score,0.45234248788368336 | |
| gpt-oss-120b,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_score_stderr,0.03576577315150716 | |
| gpt-oss-120b,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq,0.004846526655896607 | |
| gpt-oss-120b,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,idk_freq_stderr,0.0027936120600150086 | |
| gpt-oss-120b,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail,0.0 | |
| gpt-oss-120b,lexam_mcq_4_idk,lexam_mcq_4_idk:en|0,extract_fail_stderr,0.0 | |
| gpt-oss-120b,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini,25.790774299835256 | |
| gpt-oss-120b,slt,slt-paragraph_level:it-rm|0,slt_judge_gpt-4o-mini_stderr,0.8260343232284224 | |
Xet Storage Details
- Size:
- 195 kB
- Xet hash:
- 797fc1938bdf65a11dcf849ff8d25035c3dddb6e6006a2be06ba225696e332c7
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.