Mathematical Reasoning on Hard Math Stream Overall
63.9Accuracy (micro-average)EVOCHAMBER
Evaluation Results
| Method | Links | |
|---|---|---|
| EVOCHAMBERBackbone=Qwen3-8B, Team size (k)=32026.05 | 63.9 | |
| MemCollabBackbone=Qwen3-8B, Team size (k)=32026.05 | 48.4 | |
| EvoMemBackbone=Qwen3-8B, Team size (k)=32026.05 | 44.5 | |
| AgentNetBackbone=Qwen3-8B, Team size (k)=32026.05 | 41.4 | |
| DyLANBackbone=Qwen3-8B, Team size (k)=32026.05 | 40.3 | |
| SC (k=5)Backbone=Qwen3-8B, Team size (k)=52026.05 | 39 | |
| SABackbone=Qwen3-8B, Team size (k)=12026.05 | 29.8 |