Mathematical and Physics Reasoning on OLYMPIADBENCH
65.15AccuracySERO
Evaluation Results
| Method | Links | |
|---|---|---|
| SEROBackbone=Gemini-2.5-flash-lite2026.05 | 65.15 | |
| WorkflowBackbone=Gemini-2.5-flash-lite2026.05 | 60.74 | |
| Random Role EvolutionBackbone=Gemini-2.5-flash-lite2026.05 | 55.97 | |
| Static Role OrchestrationBackbone=Gemini-2.5-flash-lite2026.05 | 52.97 | |
| Static DAG MASBackbone=Gemini-2.5-flash-lite2026.05 | 51.02 | |
| SEROBackbone=Qwen3-8b2026.05 | 48.6 | |
| Static Role OrchestrationBackbone=Qwen3-8b2026.05 | 47.89 | |
| Random Role EvolutionBackbone=Qwen3-8b2026.05 | 47.54 | |
| Static DAG MASBackbone=Qwen3-8b2026.05 | 42.9 | |
| CoTBackbone=Gemini-2.5-flash-lite2026.05 | 40.93 | |
| SC@3Backbone=Gemini-2.5-flash-lite2026.05 | 40.92 | |
| SEROBackbone=GPT-4o-mini2026.05 | 40.27 | |
| WorkflowBackbone=Qwen3-8b2026.05 | 40.07 | |
| SC@3Backbone=GPT-4o-mini2026.05 | 39.61 | |
| Static Role OrchestrationBackbone=GPT-4o-mini2026.05 | 38.97 | |
| Random Role EvolutionBackbone=GPT-4o-mini2026.05 | 38.54 | |
| Static DAG MASBackbone=GPT-4o-mini2026.05 | 38.46 | |
| CoTBackbone=GPT-4o-mini2026.05 | 37.71 | |
| SC@3Backbone=Qwen3-8b2026.05 | 36.6 | |
| CoTBackbone=Qwen3-8b2026.05 | 35.57 | |
| WorkflowBackbone=GPT-4o-mini2026.05 | 34.88 |