Graduate-level Reasoning on GPQA main (Pass@10)
76.7Pass@10Multi-chain
Evaluation Results
| Method | Links | |
|---|---|---|
| Multi-chainModel=Qwen2.5-32B-Instruct2026.01 | 76.7 | |
| Entropy-TreeModel=Qwen2.5-32B-Instruct2026.01 | 75.93 | |
| Entropy-TreeModel=Qwen2.5-14B-Instruct2026.01 | 73.53 | |
| Multi-chainModel=Qwen2.5-14B-Instruct2026.01 | 72.11 | |
| Entropy-TreeModel=Qwen2.5-7B-Instruct2026.01 | 72.07 | |
| Multi-chainModel=Qwen2.5-7B-Instruct2026.01 | 71.56 |