Question Answering on DAPO 51 (test)
56.64F1 ScoreOrchMAS
Evaluation results
| Method | Links | ||
|---|---|---|---|
| OrchMASCategory=Ours2026.03 | 56.64 | 56.64 | |
| GPT-4o-miniCategory=CoT Reasoning2026.03 | 22.92 | 22.92 | |
| GPT-4o-miniCategory=Baseline2026.03 | 19.79 | 19.79 | |
| GEPACategory=MAS, Base Model=GPT-4o-mini2026.03 | 15.16 | 13.54 | |
| TextGradCategory=MAS, Base Model=GPT-4o-mini2026.03 | 12.51 | 11.46 | |
| OPROCategory=MAS, Base Model=GPT-4o-mini2026.03 | 7.31 | 7.29 | |
| Qwen3-4BCategory=GRPO2026.03 | 6.25 | 6.25 | |
| Qwen3-4BCategory=SFT2026.03 | 5.21 | 5.21 | |
| Qwen3-4BCategory=Baseline2026.03 | 0 | 0 | |
| Qwen3-4BCategory=CoT Reasoning2026.03 | 0 | 0 |