Mathematical Reasoning on MultiArith (Accuracy)
99.15AccuracyDMoA
Evaluation Results
| Method | Links | |
|---|---|---|
| DMoABackbone=gpt-oss-120b, Evaluation Paradigm=few-shot2026.05 | 99.15 | |
| SafeSieveBackbone=gpt-oss-120b2026.05 | 97.8 | |
| G-DesignerBackbone=gpt-oss-120b, Evaluation Paradigm=few-shot2026.05 | 97.6 | |
| ARG-DesignerBackbone=gpt-oss-120b, Evaluation Paradigm=few-shot2026.05 | 97.35 | |
| GPTSwarmBackbone=gpt-oss-120b2026.05 | 96.28 | |
| STEERBackbone=gpt-oss-120b2026.05 | 95.82 | |
| LLM-DebateBackbone=gpt-oss-120b2026.05 | 95.45 | |
| SpecReasonBackbone=gpt-oss-120b2026.05 | 95.4 | |
| AutoGenBackbone=gpt-oss-120b2026.05 | 95.05 | |
| Random GraphBackbone=gpt-oss-120b2026.05 | 94.8 | |
| Complete GraphBackbone=gpt-oss-120b2026.05 | 94.73 | |
| MoABackbone=gpt-oss-120b2026.05 | 94.5 | |
| SCBackbone=gpt-oss-120b2026.05 | 94.4 | |
| AFlowBackbone=gpt-oss-120b2026.05 | 94.28 | |
| CoTBackbone=gpt-oss-120b2026.05 | 93.6 | |
| VanillaBackbone=gpt-oss-120b2026.05 | 93.4 | |
| StarBackbone=gpt-oss-120b2026.05 | 93.25 | |
| TreeBackbone=gpt-oss-120b2026.05 | 92.95 | |
| ChainBackbone=gpt-oss-120b2026.05 | 92.88 |