Legal Question Answering on JEC-QA
69.49KD ScoreKimi-K2-thinking
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Kimi-K2-thinkingParameters=1T2026.01 | 69.49 | 61.19 | 65.34 | |
| DeepSeek-R12026.01 | 67.88 | 61.04 | 64.46 | |
| Qwen3-235B-A22BParameters=235B2026.01 | 65.16 | 58.98 | 62.07 | |
| LegalOne-8BParameters=8B2026.01 | 63.19 | 61.52 | 62.36 | |
| Qwen3-Max2026.01 | 62.03 | 54.22 | 58.13 | |
| GPT-52026.01 | 60.88 | 57.83 | 59.35 | |
| LegalOne-4BParameters=4B2026.01 | 58.41 | 52.95 | 55.68 | |
| GLM-4.72026.01 | 56.9 | 49.05 | 52.97 | |
| DeepSeek-v3.22026.01 | 54.58 | 45.72 | 50.15 | |
| Qwen3-8BParameters=8B2026.01 | 48.44 | 40.78 | 44.61 | |
| GPT-4o2026.01 | 46.27 | 38.18 | 42.23 | |
| Qwen3-4BParameters=4B2026.01 | 41.99 | 37.27 | 39.63 | |
| LegalOne-1.7BParameters=1.7B2026.01 | 41.94 | 40.54 | 41.24 | |
| Qwen3-1.7BParameters=1.7B2026.01 | 31.02 | 25.25 | 28.13 | |
| GPT-4o-mini2026.01 | 29.46 | 27.52 | 28.49 |