Physics Reasoning on HCV
59AccuracyQwen3-30B + RL (synthetic)
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-30B + RL (synthetic)Model=Qwen3-30B, Post-training Stage=RL (synthetic)2026.04 | 59 | |
| Qwen3-30BModel=Qwen3-30B, Post-training Stage=Instruct2026.04 | 53.9 | |
| Qwen2.5-32B + RL (synthetic)Model=Qwen2.5-32B, Post-training Stage=RL (synthetic)2026.04 | 53.9 | |
| Qwen2.5-14B + RL (synthetic)Model=Qwen2.5-14B, Post-training Stage=RL (synthetic)2026.04 | 51.7 | |
| Qwen2.5-32BModel=Qwen2.5-32B, Post-training Stage=Instruct2026.04 | 50.6 | |
| Qwen2.5-14BModel=Qwen2.5-14B, Post-training Stage=Instruct2026.04 | 49.3 | |
| Qwen2.5-7B + RL (synthetic)Model=Qwen2.5-7B, Post-training Stage=RL (synthetic)2026.04 | 46.3 | |
| Qwen2.5-7BModel=Qwen2.5-7B, Post-training Stage=Instruct2026.04 | 44.5 | |
| Qwen2.5-3B + RL (synthetic)Model=Qwen2.5-3B, Post-training Stage=RL (synthetic)2026.04 | 39.5 | |
| Qwen2.5-3BModel=Qwen2.5-3B, Post-training Stage=Instruct2026.04 | 31.9 |