Mathematical Problem Solving on Generalization Math Pool Average
86.52Average AccuracyParaManager
Evaluation Results
| Method | Links | |
|---|---|---|
| ParaManagerStrategy=Model Orchestration2026.04 | 86.52 | |
| Majority VoteModel Pool=Gemini-2.5-flash2026.04 | 84.93 | |
| Majority VoteModel Pool=GPT-OSS-120B2026.04 | 84.21 | |
| Self RefineModel Pool=Gemini-2.5-flash2026.04 | 82.66 | |
| ToolOrchestraStrategy=Model Orchestration2026.04 | 81.9 | |
| Self RefineModel Pool=GPT-OSS-120B2026.04 | 81.53 | |
| PuppeteerStrategy=Model Orchestration2026.04 | 80.47 | |
| Majority VoteModel Pool=Qwen3-235B-A22B-Instruct-25072026.04 | 76.92 | |
| Self RefineModel Pool=Qwen3-235B-A22B-Instruct-25072026.04 | 76.35 | |
| BaseModel Pool=Gemini-2.5-flash2026.04 | 74.78 | |
| BaseModel Pool=Qwen3-235B-A22B-Instruct-25072026.04 | 73.79 | |
| BaseModel Pool=GPT-OSS-120B2026.04 | 73.65 |