Mathematical Reasoning on Minerva (Pass@1 %)
38.6Pass@1 RateEurus-2-7B-PRIME
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Eurus-2-7B-PRIMECategory=Long CoT2025.10 | 38.6 | 43.6 | |
| LILOModel=Qwen2.5-Math-7B, Avg. Rollouts=4.0x2026.02 | 37.5 | 40.1 | |
| Scaf-GRPOCategory=Long CoT2025.10 | 36.4 | 50.9 | |
| OpenReasoner-ZeroCategory=Long CoT2025.10 | 35.6 | 45 | |
| GRPOModel=Qwen2.5-Math-7B, Avg. Rollouts=1.0x2026.02 | 34.9 | 37.2 | |
| Oat-ZeroCategory=Long CoT2025.10 | 34.6 | 46.5 | |
| DSModel=Qwen2.5-Math-7B, Avg. Rollouts=2.5x2026.02 | 34.5 | 39.4 | |
| MoPPSModel=Qwen2.5-Math-7B, Avg. Rollouts=1.0x2026.02 | 34.1 | 38.6 | |
| PACED-RLModel=Qwen2.5-Math-7B, Avg. Rollouts=1.0x2026.02 | 34.1 | 40.1 | |
| LUFFYCategory=Long CoT2025.10 | 33.8 | 46.6 | |
| FlowRLModel=Qwen2.5-Math-7B, Avg. Rollouts=1.0x2026.02 | 32.3 | 36.5 | |
| rStar-Math-7BCategory=Long CoT2025.10 | 32.2 | 43.6 | |
| SimpleRL-ZeroCategory=Long CoT2025.10 | 31.6 | 42.6 | |
| PACED-RLModel=Qwen2.5-Math-1.5B, Avg. Rollouts=1.0x2026.02 | 29 | 32.1 | |
| DSModel=Qwen2.5-Math-1.5B, Avg. Rollouts=2.0x2026.02 | 28.3 | 31.2 | |
| LILOModel=Qwen2.5-Math-1.5B, Avg. Rollouts=4.0x2026.02 | 27.9 | 31.2 | |
| Qwen-2.5-7B-BaseCategory=Short CoT2025.10 | 26.4 | 31.3 | |
| MoPPSModel=Qwen2.5-Math-1.5B, Avg. Rollouts=1.0x2026.02 | 26.1 | 30.4 | |
| GRPOModel=Qwen2.5-Math-1.5B, Avg. Rollouts=1.0x2026.02 | 24.2 | 29.1 | |
| FlowRLModel=Qwen2.5-Math-1.5B, Avg. Rollouts=1.0x2026.02 | 20.2 | 27.1 | |
| Qwen-2.5-Math-7B-BaseCategory=Short CoT2025.10 | 16.5 | 27.5 |