| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| CMMLU | Score61.3 | 20 | 4d ago | ||
| MMLU | MMLU Score55 | 20 | 4d ago | ||
| Gaokao | Yi | Accuracy82.8 | 10 | 4d ago | |
| LiveBench 2024-11-25 | Qwen3-VL Thinking | Score70.79 | 5 | 4d ago | |
| SuperGPQA | STEP3-VL-10B | Score50.38 | 5 | 4d ago | |
| GPQA Diamond | STEP3-VL-10B | Score70.83 | 5 | 4d ago | |
| MMLU-Pro | Qwen3-VL Thinking | Score0.7709 | 5 | 4d ago |