Mathematical Reasoning on MATH (test) (Model Performance Scores)
80.83Accuracy (MATH Test)Aflow
Evaluation Results
| Method | Links | |
|---|---|---|
| AflowMulti-agent=Yes, Automated Topology=Yes, Conditional Configuration=No2026.03 | 80.83 | |
| CARDMulti-agent=Yes, Automated Topology=Yes, Conditional Configuration=Yes2026.03 | 73.33 | |
| G-designerMulti-agent=Yes, Automated Topology=Yes, Conditional Configuration=No2026.03 | 70 | |
| GPTswarmMulti-agent=Yes, Automated Topology=Yes, Conditional Configuration=No2026.03 | 67.5 | |
| CoTMulti-agent=No, Automated Topology=No, Conditional Configuration=No2026.03 | 61.66 | |
| Random-graphMulti-agent=Yes, Automated Topology=No, Conditional Configuration=No2026.03 | 60 | |
| LLM-DebateMulti-agent=Yes, Automated Topology=No, Conditional Configuration=No2026.03 | 59.16 | |
| VanillaMulti-agent=No, Automated Topology=No, Conditional Configuration=No2026.03 | 59.16 |