Question Answering on ARC Challenge (pass@1)
94.1Pass@1Qwen3
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3Model Category=Original Models, Sampling Temperature=0.6, Shuffle options=true2026.05 | 94.1 | |
| Qwen3-8192Model Category=Original Models, Max Generation Length=8192, Sampling Temperature=0.6, Shuffle options=true2026.05 | 93.8 | |
| TGPO-annealingModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 82.8 | |
| TGPOModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 81.2 | |
| LUFFYModel Category=Off-Policy and Mixed-Policy, Sampling Temperature=0.6, Shuffle options=true2026.05 | 80.1 | |
| TGPORModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 80.1 | |
| KDRLModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 78.4 | |
| GRPO++Model Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 77.4 | |
| PRIME-ZeroModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 73.3 | |
| SFTModel Category=Off-Policy and Mixed-Policy, Sampling Temperature=0.6, Shuffle options=true2026.05 | 73.1 | |
| Oat-ZeroModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 70.1 | |
| SimpleRL-ZeroModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 30.2 | |
| DS-MTPModel Size=3B2025.10 | 27.4 | |
| NTPModel Size=3B2025.10 | 26.3 | |
| OP DistillModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.05 | 26.1 | |
| FSP-RevLMModel Size=3B2025.10 | 25.5 | |
| MTPModel Size=3B2025.10 | 24.5 | |
| Qwen2.5-Math-7BModel Category=Original Models, Sampling Temperature=0.6, Shuffle options=true2026.05 | 18.2 |