List your company

Medical Reasoning on DiSCQ

98.37AccuracyCOTCAgent
95.468496.221796.97597.7283May 14, 2026

Evaluation results

MethodLinks
COTCAgentBackbone=Baichuan-M22026.0598.3798.2
COTCAgentBackbone=Gemini 2.5 Pro2026.0598.2698.3
COTCAgentBackbone=GPT-4o2026.0598.1898.2
COTCAgentBackbone=Claude 3.7 Sonnet2026.0598.1498.2
API toolsBackbone=Gemini 2.5 Pro2026.0597.9298
API toolsBackbone=Claude 3.7 Sonnet2026.0597.8897.9
KAREBackbone=Gemini 2.5 Pro2026.0597.8798
Google'sBackbone=Baichuan-M22026.0597.8697.8
API toolsBackbone=GPT-4o2026.0597.8497.9
KAREBackbone=Claude 3.7 Sonnet2026.0597.7997.9
KAREBackbone=GPT-4o2026.0597.7697.9
API toolsBackbone=Baichuan-M22026.0597.7698.1
Google'sBackbone=Gemini 2.5 Pro2026.0597.6897.8
KAREBackbone=Baichuan-M22026.0597.6897.3
Google'sBackbone=GPT-4o2026.0597.5897.7
Google'sBackbone=Claude 3.7 Sonnet2026.0597.5797.7
DirPredBackbone=Baichuan-M22026.0597.4797.9
DirPredBackbone=Gemini 2.5 Pro2026.0597.4697.3
DirPredBackbone=Claude 3.7 Sonnet2026.0597.3897.2
DirPredBackbone=GPT-4o2026.0597.3697.2
COTCAgentBackbone=Qwen3-Next-80B-A3B2026.0597.0997.1
TimeCAPBackbone=Baichuan-M22026.0597.0796.9
TimeCAPBackbone=Gemini 2.5 Pro2026.0597.0697.1
TimeCAPBackbone=GPT-4o2026.0596.9696.9
TimeCAPBackbone=Claude 3.7 Sonnet2026.0596.9497
API toolsBackbone=Qwen3-Next-80B-A3B2026.0596.6196.7
KAREBackbone=Qwen3-Next-80B-A3B2026.0596.4796.8
Google'sBackbone=Qwen3-Next-80B-A3B2026.0596.2496.1
DirPredBackbone=Qwen3-Next-80B-A3B2026.0595.9795.7
TimeCAPBackbone=Qwen3-Next-80B-A3B2026.0595.5894.8