Mathematical Reasoning on OlymMATH Easy
41.62Pass@1e3-1.7B + InT+ RL
Evaluation Results
| Method | Links | |
|---|---|---|
| e3-1.7B + InT+ RLRL Data Size=64, Evaluation Protocol=8 rollouts avg.2026.01 | 41.62 | |
| e3-1.7B + RLRL Data Size=1216, Evaluation Protocol=8 rollouts avg.2026.01 | 38.75 | |
| e3-1.7B + Distill + RLRL Data Size=1216, Evaluation Protocol=8 rollouts avg.2026.01 | 37.38 | |
| Fixed-MAS + ADv2Framework=Fixed-MAS, Technique=ADv22026.02 | 32.5 | |
| Dynamic-MAS + ADv2Framework=Dynamic-MAS, Technique=ADv22026.02 | 32 | |
| Fixed-MASFramework=Fixed-MAS2026.02 | 31.25 | |
| Dynamic-MAS + Multi-TAGFramework=Dynamic-MAS, Technique=Multi-TAG2026.02 | 27 | |
| Fixed-MAS + Self-RefineFramework=Fixed-MAS, Technique=Self-Refine2026.02 | 26.25 | |
| Dynamic-MASFramework=Dynamic-MAS2026.02 | 26 | |
| Fixed-MAS + ADv1Framework=Fixed-MAS, Technique=ADv12026.02 | 25 | |
| Single Agent + CoTFramework=Single Agent, Technique=Chain-of-Thought2026.02 | 24 | |
| Dynamic-MAS + PRMFramework=Dynamic-MAS, Technique=PRM2026.02 | 24 | |
| Fixed-MAS + PRMFramework=Fixed-MAS, Technique=PRM2026.02 | 21.25 | |
| Single AgentFramework=Single Agent2026.02 | 20 | |
| Fixed-MAS + Multi-TAGFramework=Fixed-MAS, Technique=Multi-TAG2026.02 | 20 | |
| Dynamic-MAS + Self-RefineFramework=Dynamic-MAS, Technique=Self-Refine2026.02 | 20 |