List your company

Mathematical Reasoning on AIME 24 (Accuracy and Cost)

93.3AccuracyQwen3-235B
39.63653.56867.581.432Jun 28, 2026

Evaluation results

MethodLinks
Qwen3-235BMethod Category=Heuristic, Parameters=235B2026.0693.30.4553
ENTROROUTERMethod Category=Routing Architecture2026.0690.60.2881
FORCMethod Category=Existing Routing Architecture2026.06900.3435
Qwen3-30BMethod Category=Heuristic, Parameters=30B2026.0687.50.2126
RandomMethod Category=Heuristic2026.0684.60.2179
RouteLLMMethod Category=Existing Routing Architecture2026.0680.40.0433
Qwen3-4BMethod Category=Heuristic, Parameters=4B2026.0676.90.0173
Router-R1Method Category=Existing Routing Architecture2026.0641.70.0198
xRouterMethod Category=Existing Routing Architecture2026.0641.70.0018