General Provision Prediction on LeCaRD v2
66.67PrecisionDISC-LawLLM
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| DISC-LawLLM2025.11 | 66.67 | 2.13 | 4.12 | |
| DISC-LawLLM2026.05 | 66.67 | 2.13 | 4.12 | |
| L4L2025.11 | 64.05 | 40.77 | 45.51 | |
| GPT-5.22025.11 | 52.01 | 37.38 | 39.08 | |
| Claude 4 Sonnet2025.11 | 36.85 | 24.05 | 26.05 | |
| GPT o4-mini2025.11 | 34.8 | 23.24 | 25.52 | |
| L4L2025.11 | 34 | 45.95 | 39.08 | |
| GPT-4o2025.11 | 34 | 23.27 | 24.85 | |
| LexGuard2026.05 | 34 | 45.95 | 39.08 | |
| Claude 4 Sonnet2025.11 | 32.79 | 26.67 | 29.41 | |
| Claude 4 Sonnet2026.05 | 32.79 | 26.67 | 29.41 | |
| DeepSeek v32025.11 | 32.16 | 22.95 | 23.29 | |
| GPT-5.22025.11 | 23.47 | 46.25 | 31.14 | |
| GPT 5.22026.05 | 23.47 | 46.25 | 31.14 | |
| GPT o4-mini2025.11 | 21.54 | 35 | 26.67 | |
| GPT o4-mini2026.05 | 21.54 | 35 | 26.67 | |
| GPT-4o2025.11 | 12 | 36 | 18 | |
| GPT-4o2026.05 | 12 | 36 | 18 | |
| DeepSeek v32025.11 | 10.25 | 44.84 | 16.88 | |
| DeepSeek v32026.05 | 10.25 | 44.84 | 16.88 | |
| LexiLaw2025.11 | 8.96 | 26.27 | 13.36 | |
| LexiLaw2026.05 | 8.96 | 26.27 | 13.36 | |
| LexiLaw2025.11 | 1.03 | 0.21 | 0.34 | |
| DISC-LawLLM2025.11 | 0 | 0 | 0 |