Graduate-level Reasoning on SuperGPQA (Pass@1)
36Pass@1Rule+CER
Evaluation Results
| Method | Links | |
|---|---|---|
| Rule+CERBackbone=Qwen3-8B-Base, Training Dataset=mathematical dataset2026.03 | 36 | |
| Rule-basedBackbone=Qwen3-8B-Base, Training Dataset=mathematical dataset2026.03 | 35.1 | |
| CERBackbone=Qwen3-8B-Base, Training Dataset=mathematical dataset2026.03 | 35 | |
| General-verifierBackbone=Qwen3-8B-Base, Training Dataset=mathematical dataset2026.03 | 34.9 | |
| Exact-matchBackbone=Qwen3-8B-Base, Training Dataset=mathematical dataset2026.03 | 33.5 | |
| VeriFreeBackbone=Qwen3-8B-Base, Training Dataset=mathematical dataset2026.03 | 32.4 | |
| Rule-basedBackbone=Qwen3-4B-Base, Training Dataset=mathematical dataset2026.03 | 32.2 | |
| CERBackbone=Qwen3-4B-Base, Training Dataset=mathematical dataset2026.03 | 32.1 | |
| Rule+CERBackbone=Qwen3-4B-Base, Training Dataset=mathematical dataset2026.03 | 31.3 | |
| VeriFreeBackbone=Qwen3-4B-Base, Training Dataset=mathematical dataset2026.03 | 30.9 | |
| General-verifierBackbone=Qwen3-4B-Base, Training Dataset=mathematical dataset2026.03 | 30.9 | |
| BaseBackbone=Qwen3-8B-Base, Training Dataset=mathematical dataset2026.03 | 27 | |
| Exact-matchBackbone=Qwen3-4B-Base, Training Dataset=mathematical dataset2026.03 | 24.2 | |
| BaseBackbone=Qwen3-4B-Base, Training Dataset=mathematical dataset2026.03 | 21 |