Mathematical Reasoning on AIME Average
44.01Avg@32PMD-MEAN
Evaluation Results
| Method | Links | |
|---|---|---|
| PMD-MEANBackbone=Qwen3-30B-A3B-Base, tau=0.1, Staleness=162026.02 | 44.01 | |
| PMD-MEANBackbone=Qwen3-30B-A3B-Base, tau=0.01, Staleness=162026.02 | 42.55 | |
| GRPOBackbone=Qwen3-30B-A3B-Base, tau=null, Staleness=162026.02 | 32.24 | |
| PMD-MEANBackbone=Qwen2.5-7B, tau=0.005, Staleness=162026.02 | 19.58 | |
| PMD-MEANBackbone=Qwen2.5-7B, tau=0.02, Staleness=162026.02 | 19.58 | |
| On-policyBackbone=Qwen2.5-7B, tau=null, Staleness=12026.02 | 18.49 | |
| PMD-MEANBackbone=Qwen2.5-7B, tau=0.01, Staleness=162026.02 | 17.55 | |
| GRPOBackbone=Qwen2.5-7B, tau=null, Staleness=162026.02 | 13.8 |