List your company

Multi-step Reasoning on Checkmate

90AccuracyeMoT
47.56858.58469.680.616Jun 1, 2026

Evaluation results

MethodLinks
eMoTModels=Qwen-32B2026.0690
BoTModels=GPT-42026.0686.4
ToTModels=GPT-42026.0649.2