| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Xiezhi EN | Qwen3-14B | Accuracy70.85 | 8 | 1mo ago | |
| GPQA | Llama-3.3-70B-Instruct | Accuracy51.52 | 8 | 1mo ago | |
| MMLU-Pro | Qwen3.5-9B | Accuracy75.25 | 8 | 1mo ago | |
| ARC Challenge | Llama-3.3-70B-Instruct | Accuracy95.99 | 7 | 1mo ago | |
| MMLU-Redux | Qwen3.5-9B | Accuracy (English Knowledge)83.43 | 7 | 1mo ago |