List your company

Mathematical Reasoning on OlymMATH Easy

41.62Pass@1e3-1.7B + InT+ RL
19.135224.972630.8136.6474Jan 20, 2026Jan 26, 2026Feb 1, 2026Feb 7, 2026Feb 13, 2026Feb 19, 2026Feb 26, 2026

Evaluation results

MethodLinks
e3-1.7B + InT+ RLRL Data Size=64, Evaluation Protocol=8 rollouts avg.2026.0141.62
e3-1.7B + RLRL Data Size=1216, Evaluation Protocol=8 rollouts avg.2026.0138.75
e3-1.7B + Distill + RLRL Data Size=1216, Evaluation Protocol=8 rollouts avg.2026.0137.38
Fixed-MAS + ADv2Framework=Fixed-MAS, Technique=ADv22026.0232.5
Dynamic-MAS + ADv2Framework=Dynamic-MAS, Technique=ADv22026.0232
Fixed-MASFramework=Fixed-MAS2026.0231.25
Dynamic-MAS + Multi-TAGFramework=Dynamic-MAS, Technique=Multi-TAG2026.0227
Fixed-MAS + Self-RefineFramework=Fixed-MAS, Technique=Self-Refine2026.0226.25
Dynamic-MASFramework=Dynamic-MAS2026.0226
Fixed-MAS + ADv1Framework=Fixed-MAS, Technique=ADv12026.0225
Single Agent + CoTFramework=Single Agent, Technique=Chain-of-Thought2026.0224
Dynamic-MAS + PRMFramework=Dynamic-MAS, Technique=PRM2026.0224
Fixed-MAS + PRMFramework=Fixed-MAS, Technique=PRM2026.0221.25
Single AgentFramework=Single Agent2026.0220
Fixed-MAS + Multi-TAGFramework=Fixed-MAS, Technique=Multi-TAG2026.0220
Dynamic-MAS + Self-RefineFramework=Dynamic-MAS, Technique=Self-Refine2026.0220