Scientific Question Answering on GPQA Diamond (pass@1)
65.2pass@1Qwen3
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3Model Category=Original Models, Sampling Temperature=0.6, Shuffle options=true2026.05 | 65.2 | |
| Qwen3-8192Model Category=Original Models, Max Generation Length=8192, Sampling Temperature=0.6, Shuffle options=true2026.05 | 49 | |
| LUFFYModel Category=Off-Policy and Mixed-Policy, Sampling Temperature=0.6, Shuffle options=true2026.05 | 38.9 | |
| TGPOModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 37.9 | |
| TGPO-annealingModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 37.4 | |
| KDRLModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 35.4 | |
| TGPORModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 33.3 | |
| GRPO++Model Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 32.3 | |
| Oat-ZeroModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 23.7 | |
| SimpleRL-ZeroModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 23.2 | |
| SFTModel Category=Off-Policy and Mixed-Policy, Sampling Temperature=0.6, Shuffle options=true2026.05 | 20.2 | |
| PRIME-ZeroModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 18.2 | |
| Qwen2.5-Math-7BModel Category=Original Models, Sampling Temperature=0.6, Shuffle options=true2026.05 | 11.1 | |
| OP DistillModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 6.1 |