summary.csv

model,lexam_mcq_16_idk,lexam_mcq_4_idk,lexam_mcq_8_idk,lexam_oq,sdst,slds,slt,sscprt
Apertus-v1.5-70B,0.2555100072341452,0.4352291652372427,0.3242737169884762,43.66974111442829,71.68427540059871,37.99205883385756,67.05601317957166,56.88333333333333
DeepSeek-V4-Flash,0.4659995177236556,0.6204747038753501,0.52950739749079,63.06368628647388,65.6973058637084,50.9665848972364,63.92339373970346,54.225
DeepSeek-V4-Pro,0.4736918254159633,0.6242288907878568,0.5462839551314563,63.64377083832727,69.22037330515936,50.48812085822786,62.22981878088963,61.21666666666667
GLM-5.2,0.3800900249176111,0.5075512565415635,0.4489793310608115,58.76855019721502,71.01338263778834,52.26525150370471,67.25453047775947,60.46666666666667
Hy-MT2-30B-A3B,,,,,66.60371544285965,,63.44975288303131,55.75833333333333
Inkling,0.5085242343863033,0.7144845341533548,0.5971738950944198,67.65925929961429,70.94867054058814,53.36165164216092,68.57825370675452,62.525000000000006
Kimi-K2.6,0.4397114379873,0.6785418005127213,0.5483608748815576,63.86879208524918,70.11357633386159,49.81481481481481,66.34390444810543,59.55
Kimi-K3,0.4125070331966883,0.6262155300927514,0.5231174044498964,58.15541850988254,70.9896108469801,50.96805223210478,69.05560131795717,60.66666666666666
LFM2.5-8B-A1B,0.1751587492966803,0.3288589766780396,0.2657140161121006,24.510710627819304,41.97041732699419,11.084235054504592,40.98064250411862,30.3
Llama-3.3-70B-Instruct,0.3154891085925568,0.5446167376700495,0.4099945742560243,40.19784697857874,68.11850677936256,16.101629870423043,62.94151565074135,51.25833333333333
MiniMax-M3,0.3966200466200466,0.6241984830433942,0.5005848401567962,63.38698816709888,66.98890649762282,49.54910179039936,65.82784184514003,59.10833333333333
Mistral-Medium-3.5-128B,0.3734707820914718,0.5754080875244042,0.4602446302827284,52.81302708710149,65.47675647120973,33.970394951364746,58.46993410214168,52.125
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4,0.4167751788441443,0.6306402467549479,0.4866862858423467,66.45294079191092,69.56374361683395,55.13290040684054,63.65856672158154,57.025
Olmo-3.1-32B-Think,0.2396993810786914,0.3265526662134093,0.2639565468678124,33.596809692954736,35.180489522803306,26.76093979662989,40.98682042833608,27.308333333333334
Qwen3.5-35B-A3B,0.4013905634595289,0.6428633803431865,0.4750229021439552,40.09468500076271,67.17599929565064,46.71605439924551,63.80642504118616,56.34166666666667
gemma-4-31B-it,0.4622940278112691,0.6640123564598523,0.5545130001611996,57.82302948419012,63.46627927452016,48.04011718612829,48.92504118616145,59.15833333333333
gpt-oss-120b,0.3579414838035528,0.588225341658298,0.4158252831805868,55.60991740940095,63.79820390913893,46.26815356599997,59.46952224052718,52.16666666666666