Coding Ability on DS-1000
64.34AccuracyDMoA
Evaluation Results
| Method | Links | |
|---|---|---|
| DMoABackbone=gpt-oss-120b, Evaluation Paradigm=few-shot2026.05 | 64.34 | |
| ARG-DesignerBackbone=gpt-oss-120b, Evaluation Paradigm=few-shot2026.05 | 55.6 | |
| G-DesignerBackbone=gpt-oss-120b, Evaluation Paradigm=few-shot2026.05 | 54.82 | |
| SafeSieveBackbone=gpt-oss-120b2026.05 | 53.73 | |
| GPTSwarmBackbone=gpt-oss-120b2026.05 | 52.35 | |
| STEERBackbone=gpt-oss-120b2026.05 | 51.34 | |
| SpecReasonBackbone=gpt-oss-120b2026.05 | 50.08 | |
| LLM-DebateBackbone=gpt-oss-120b2026.05 | 49.26 | |
| AutoGenBackbone=gpt-oss-120b2026.05 | 48.55 | |
| Random GraphBackbone=gpt-oss-120b2026.05 | 47.48 | |
| AFlowBackbone=gpt-oss-120b2026.05 | 46.82 | |
| Complete GraphBackbone=gpt-oss-120b2026.05 | 45.05 | |
| TreeBackbone=gpt-oss-120b2026.05 | 43.5 | |
| CoTBackbone=gpt-oss-120b2026.05 | 42.35 | |
| StarBackbone=gpt-oss-120b2026.05 | 41.82 | |
| MoABackbone=gpt-oss-120b2026.05 | 39.75 | |
| VanillaBackbone=gpt-oss-120b2026.05 | 38.4 | |
| ChainBackbone=gpt-oss-120b2026.05 | 38.25 | |
| SCBackbone=gpt-oss-120b2026.05 | 37.66 |