List your company

Mathematical and Physics Reasoning on OLYMPIADBENCH

65.15AccuracySERO
33.669241.842150.01558.1879May 27, 2026

Evaluation results

MethodLinks
SEROBackbone=Gemini-2.5-flash-lite2026.0565.15
WorkflowBackbone=Gemini-2.5-flash-lite2026.0560.74
Random Role EvolutionBackbone=Gemini-2.5-flash-lite2026.0555.97
Static Role OrchestrationBackbone=Gemini-2.5-flash-lite2026.0552.97
Static DAG MASBackbone=Gemini-2.5-flash-lite2026.0551.02
SEROBackbone=Qwen3-8b2026.0548.6
Static Role OrchestrationBackbone=Qwen3-8b2026.0547.89
Random Role EvolutionBackbone=Qwen3-8b2026.0547.54
Static DAG MASBackbone=Qwen3-8b2026.0542.9
CoTBackbone=Gemini-2.5-flash-lite2026.0540.93
SC@3Backbone=Gemini-2.5-flash-lite2026.0540.92
SEROBackbone=GPT-4o-mini2026.0540.27
WorkflowBackbone=Qwen3-8b2026.0540.07
SC@3Backbone=GPT-4o-mini2026.0539.61
Static Role OrchestrationBackbone=GPT-4o-mini2026.0538.97
Random Role EvolutionBackbone=GPT-4o-mini2026.0538.54
Static DAG MASBackbone=GPT-4o-mini2026.0538.46
CoTBackbone=GPT-4o-mini2026.0537.71
SC@3Backbone=Qwen3-8b2026.0536.6
CoTBackbone=Qwen3-8b2026.0535.57
WorkflowBackbone=GPT-4o-mini2026.0534.88