Policy Question Answering on PolicyBench
64.34AccuracyDeepseek-R1
Evaluation Results
| Method | Links | |
|---|---|---|
| Deepseek-R12026.04 | 64.34 | |
| Claude-3.7-sonnet2026.04 | 64.13 | |
| Gemini-2.5-Flash2026.04 | 63.82 | |
| Claude-3.5-Sonnet2026.04 | 63.75 | |
| o4-mini2026.04 | 62.98 | |
| QwQ-32B2026.04 | 61.67 | |
| Gemini-2.0-Flash2026.04 | 60.1 | |
| GPT-4o2026.04 | 59.47 | |
| LLaMA-42026.04 | 59.17 | |
| Deepseek-V32026.04 | 59.1 | |
| Gemma 3-27B2026.04 | 58.21 |