Update README.md
Browse files
README.md
CHANGED
|
@@ -8,40 +8,58 @@ pinned: false
|
|
| 8 |
license: apache-2.0
|
| 9 |
short_description: ALL Bench Leaderboard
|
| 10 |
models:
|
| 11 |
-
# LLM - Open Source
|
|
|
|
|
|
|
| 12 |
- Qwen/Qwen3.5-122B-A10B
|
| 13 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
- Qwen/Qwen3.5-35B-A3B
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
- Qwen/Qwen3.5-9B
|
| 16 |
- Qwen/Qwen3.5-4B
|
| 17 |
-
-
|
| 18 |
- deepseek-ai/DeepSeek-V3
|
| 19 |
- deepseek-ai/DeepSeek-R1
|
| 20 |
- zai-org/GLM-5
|
| 21 |
- meta-llama/Llama-4-Scout-17B-16E-Instruct
|
| 22 |
- meta-llama/Llama-4-Maverick-17B-128E-Instruct
|
| 23 |
-
- microsoft/phi-4
|
| 24 |
-
- upstage/Solar-Open-100B
|
| 25 |
- K-intelligence/Midm-2.0-Base-Instruct
|
| 26 |
- Nanbeige/Nanbeige4.1-3B
|
| 27 |
-
- MiniMaxAI/MiniMax-M2.5
|
| 28 |
- stepfun-ai/Step-3.5-Flash
|
| 29 |
-
|
| 30 |
-
# VLM - Open Source
|
|
|
|
| 31 |
- OpenGVLab/InternVL3-78B
|
| 32 |
- Qwen/Qwen2.5-VL-72B-Instruct
|
| 33 |
- Qwen/Qwen3-VL-30B-A3B
|
| 34 |
-
#
|
|
|
|
|
|
|
| 35 |
- black-forest-labs/FLUX.1-dev
|
| 36 |
- stabilityai/stable-diffusion-3.5-large
|
| 37 |
-
|
|
|
|
| 38 |
- Lightricks/LTX-Video
|
| 39 |
-
|
|
|
|
| 40 |
- facebook/musicgen-large
|
| 41 |
- facebook/jasco-chords-drums-melody-1B
|
| 42 |
datasets:
|
| 43 |
- FINAL-Bench/Metacognitive
|
| 44 |
- FINAL-Bench/ALL-Bench-Leaderboard
|
|
|
|
| 45 |
---
|
| 46 |
|
| 47 |
|
|
|
|
| 8 |
license: apache-2.0
|
| 9 |
short_description: ALL Bench Leaderboard
|
| 10 |
models:
|
| 11 |
+
# ===== LLM - Open Source =====
|
| 12 |
+
# --- Flagship / Large ---
|
| 13 |
+
- Qwen/Qwen3.5-397B-A17B # π μΆκ° β μ€νμμ€ μ΅λ νλκ·Έμ (17B/397B MoE)
|
| 14 |
- Qwen/Qwen3.5-122B-A10B
|
| 15 |
+
- nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
|
| 16 |
+
- openai/gpt-oss-120b # π μΆκ° β Nemotron μ§μ κ²½μ (5.1B/116.8B MoE)
|
| 17 |
+
- upstage/Solar-Open-100B
|
| 18 |
+
- moonshotai/Kimi-K2 # π μΆκ° β FINAL Bench 1μ (68.71), Union Eval 62.4
|
| 19 |
+
- Qwen/Qwen3-Next-80B-A3B-Thinking
|
| 20 |
+
|
| 21 |
+
# --- Medium ---
|
| 22 |
- Qwen/Qwen3.5-35B-A3B
|
| 23 |
+
- Qwen/Qwen3.5-27B
|
| 24 |
+
- mistralai/Mistral-Large-Instruct-2411 # π μΆκ° β μ λ½ λν μ€ν λͺ¨λΈ
|
| 25 |
+
- LGAI-EXAONE/EXAONE-Deep-32B # π μΆκ° β νκ΅ μλ²λ¦° AI (K-EXAONE)
|
| 26 |
+
- MiniMaxAI/MiniMax-M2.5
|
| 27 |
+
- openai/gpt-oss-20b # π μΆκ° β AIME 98.7% μν MoE μ±νΌμΈ
|
| 28 |
+
|
| 29 |
+
# --- Small / Edge ---
|
| 30 |
- Qwen/Qwen3.5-9B
|
| 31 |
- Qwen/Qwen3.5-4B
|
| 32 |
+
- microsoft/phi-4
|
| 33 |
- deepseek-ai/DeepSeek-V3
|
| 34 |
- deepseek-ai/DeepSeek-R1
|
| 35 |
- zai-org/GLM-5
|
| 36 |
- meta-llama/Llama-4-Scout-17B-16E-Instruct
|
| 37 |
- meta-llama/Llama-4-Maverick-17B-128E-Instruct
|
|
|
|
|
|
|
| 38 |
- K-intelligence/Midm-2.0-Base-Instruct
|
| 39 |
- Nanbeige/Nanbeige4.1-3B
|
|
|
|
| 40 |
- stepfun-ai/Step-3.5-Flash
|
| 41 |
+
|
| 42 |
+
# ===== VLM - Open Source =====
|
| 43 |
+
- OpenGVLab/InternVL3.5-241B-A28B # π μΆκ° β VLM μ€νμμ€ 1μ (MMMU 77.7)
|
| 44 |
- OpenGVLab/InternVL3-78B
|
| 45 |
- Qwen/Qwen2.5-VL-72B-Instruct
|
| 46 |
- Qwen/Qwen3-VL-30B-A3B
|
| 47 |
+
- moonshotai/Kimi-VL-A3B-Thinking # π μΆκ° β VLM κ²½λ μΆλ‘ λν
|
| 48 |
+
|
| 49 |
+
# ===== Image Generation =====
|
| 50 |
- black-forest-labs/FLUX.1-dev
|
| 51 |
- stabilityai/stable-diffusion-3.5-large
|
| 52 |
+
|
| 53 |
+
# ===== Video Generation =====
|
| 54 |
- Lightricks/LTX-Video
|
| 55 |
+
|
| 56 |
+
# ===== Music Generation =====
|
| 57 |
- facebook/musicgen-large
|
| 58 |
- facebook/jasco-chords-drums-melody-1B
|
| 59 |
datasets:
|
| 60 |
- FINAL-Bench/Metacognitive
|
| 61 |
- FINAL-Bench/ALL-Bench-Leaderboard
|
| 62 |
+
- ginigen-ai/smol-worldcup
|
| 63 |
---
|
| 64 |
|
| 65 |
|