List your company

Mathematical Reasoning on MATH hard Level 4 5

76.3Accuracy (Exact Match)EVOCHAMBER
35.84446.34756.8567.353May 11, 2026

Evaluation results

MethodLinks
EVOCHAMBERBackbone=Qwen3-8B, Team size (k)=32026.0576.3
MemCollabBackbone=Qwen3-8B, Team size (k)=32026.0560.3
EvoMemBackbone=Qwen3-8B, Team size (k)=32026.0555.3
SC (k=5)Backbone=Qwen3-8B, Team size (k)=52026.0554.2
DyLANBackbone=Qwen3-8B, Team size (k)=32026.0554.2
AgentNetBackbone=Qwen3-8B, Team size (k)=32026.0549.6
SABackbone=Qwen3-8B, Team size (k)=12026.0537.4