List your company

Medical Reasoning on Time-MMD

85.33AccuracyCOTCAgent
72.725275.997679.2782.5424May 14, 2026

Evaluation results

MethodLinks
COTCAgentBackbone=Baichuan-M22026.0585.3383.9
KAREBackbone=Baichuan-M22026.0585.0682.9
COTCAgentBackbone=Gemini 2.5 Pro2026.0584.9783.7
COTCAgentBackbone=Claude 3.7 Sonnet2026.0584.7683.1
API toolsBackbone=Baichuan-M22026.0584.7182.6
COTCAgentBackbone=GPT-4o2026.0584.5282.8
Google'sBackbone=Baichuan-M22026.0583.4281.6
KAREBackbone=Gemini 2.5 Pro2026.0582.9781.6
DirPredBackbone=Baichuan-M22026.0582.8180.8
API toolsBackbone=Gemini 2.5 Pro2026.0582.7381.7
KAREBackbone=Claude 3.7 Sonnet2026.0582.7181.4
KAREBackbone=GPT-4o2026.0582.5480.8
API toolsBackbone=Claude 3.7 Sonnet2026.0582.4881.5
API toolsBackbone=GPT-4o2026.0582.0780.6
Google'sBackbone=Gemini 2.5 Pro2026.0581.7480.6
TimeCAPBackbone=Baichuan-M22026.0581.6479.6
Google'sBackbone=Claude 3.7 Sonnet2026.0581.5180.4
DirPredBackbone=Gemini 2.5 Pro2026.0581.2979.6
Google'sBackbone=GPT-4o2026.0581.2279.9
DirPredBackbone=Claude 3.7 Sonnet2026.0581.0679.4
DirPredBackbone=GPT-4o2026.0580.9178.8
TimeCAPBackbone=Gemini 2.5 Pro2026.0580.0878.6
TimeCAPBackbone=Claude 3.7 Sonnet2026.0579.8978.4
TimeCAPBackbone=GPT-4o2026.0579.6477.9
COTCAgentBackbone=Qwen3-Next-80B-A3B2026.0577.5476.3
KAREBackbone=Qwen3-Next-80B-A3B2026.0576.4175.8
API toolsBackbone=Qwen3-Next-80B-A3B2026.0575.5274.8
Google'sBackbone=Qwen3-Next-80B-A3B2026.0574.8973.6
DirPredBackbone=Qwen3-Next-80B-A3B2026.0574.0672.7
TimeCAPBackbone=Qwen3-Next-80B-A3B2026.0573.2171.8