Medical Reasoning on Time-MMD
85.33AccuracyCOTCAgent
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| COTCAgentBackbone=Baichuan-M22026.05 | 85.33 | 83.9 | |
| KAREBackbone=Baichuan-M22026.05 | 85.06 | 82.9 | |
| COTCAgentBackbone=Gemini 2.5 Pro2026.05 | 84.97 | 83.7 | |
| COTCAgentBackbone=Claude 3.7 Sonnet2026.05 | 84.76 | 83.1 | |
| API toolsBackbone=Baichuan-M22026.05 | 84.71 | 82.6 | |
| COTCAgentBackbone=GPT-4o2026.05 | 84.52 | 82.8 | |
| Google'sBackbone=Baichuan-M22026.05 | 83.42 | 81.6 | |
| KAREBackbone=Gemini 2.5 Pro2026.05 | 82.97 | 81.6 | |
| DirPredBackbone=Baichuan-M22026.05 | 82.81 | 80.8 | |
| API toolsBackbone=Gemini 2.5 Pro2026.05 | 82.73 | 81.7 | |
| KAREBackbone=Claude 3.7 Sonnet2026.05 | 82.71 | 81.4 | |
| KAREBackbone=GPT-4o2026.05 | 82.54 | 80.8 | |
| API toolsBackbone=Claude 3.7 Sonnet2026.05 | 82.48 | 81.5 | |
| API toolsBackbone=GPT-4o2026.05 | 82.07 | 80.6 | |
| Google'sBackbone=Gemini 2.5 Pro2026.05 | 81.74 | 80.6 | |
| TimeCAPBackbone=Baichuan-M22026.05 | 81.64 | 79.6 | |
| Google'sBackbone=Claude 3.7 Sonnet2026.05 | 81.51 | 80.4 | |
| DirPredBackbone=Gemini 2.5 Pro2026.05 | 81.29 | 79.6 | |
| Google'sBackbone=GPT-4o2026.05 | 81.22 | 79.9 | |
| DirPredBackbone=Claude 3.7 Sonnet2026.05 | 81.06 | 79.4 | |
| DirPredBackbone=GPT-4o2026.05 | 80.91 | 78.8 | |
| TimeCAPBackbone=Gemini 2.5 Pro2026.05 | 80.08 | 78.6 | |
| TimeCAPBackbone=Claude 3.7 Sonnet2026.05 | 79.89 | 78.4 | |
| TimeCAPBackbone=GPT-4o2026.05 | 79.64 | 77.9 | |
| COTCAgentBackbone=Qwen3-Next-80B-A3B2026.05 | 77.54 | 76.3 | |
| KAREBackbone=Qwen3-Next-80B-A3B2026.05 | 76.41 | 75.8 | |
| API toolsBackbone=Qwen3-Next-80B-A3B2026.05 | 75.52 | 74.8 | |
| Google'sBackbone=Qwen3-Next-80B-A3B2026.05 | 74.89 | 73.6 | |
| DirPredBackbone=Qwen3-Next-80B-A3B2026.05 | 74.06 | 72.7 | |
| TimeCAPBackbone=Qwen3-Next-80B-A3B2026.05 | 73.21 | 71.8 |