Legal Reasoning on PRBench-Legal 500 prompts
44.1GPT-5 Grader Score
Qwen3.5-4B RL on Agentic Self-Instruct data
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| 44.1 | 39.3 | ||
2026.06 | 40.4 | 35.8 | |
| 37.7 | 34.3 | ||
2026.06 | 28 | 24.5 |
Qwen3.5-4B RL on Agentic Self-Instruct data
| Method | Links | ||
|---|---|---|---|
| 44.1 | 39.3 | ||
2026.06 | 40.4 | 35.8 | |
| 37.7 | 34.3 | ||
2026.06 | 28 | 24.5 |