Medical Reasoning on DiSCQ
98.37AccuracyCOTCAgent
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| COTCAgentBackbone=Baichuan-M22026.05 | 98.37 | 98.2 | |
| COTCAgentBackbone=Gemini 2.5 Pro2026.05 | 98.26 | 98.3 | |
| COTCAgentBackbone=GPT-4o2026.05 | 98.18 | 98.2 | |
| COTCAgentBackbone=Claude 3.7 Sonnet2026.05 | 98.14 | 98.2 | |
| API toolsBackbone=Gemini 2.5 Pro2026.05 | 97.92 | 98 | |
| API toolsBackbone=Claude 3.7 Sonnet2026.05 | 97.88 | 97.9 | |
| KAREBackbone=Gemini 2.5 Pro2026.05 | 97.87 | 98 | |
| Google'sBackbone=Baichuan-M22026.05 | 97.86 | 97.8 | |
| API toolsBackbone=GPT-4o2026.05 | 97.84 | 97.9 | |
| KAREBackbone=Claude 3.7 Sonnet2026.05 | 97.79 | 97.9 | |
| KAREBackbone=GPT-4o2026.05 | 97.76 | 97.9 | |
| API toolsBackbone=Baichuan-M22026.05 | 97.76 | 98.1 | |
| Google'sBackbone=Gemini 2.5 Pro2026.05 | 97.68 | 97.8 | |
| KAREBackbone=Baichuan-M22026.05 | 97.68 | 97.3 | |
| Google'sBackbone=GPT-4o2026.05 | 97.58 | 97.7 | |
| Google'sBackbone=Claude 3.7 Sonnet2026.05 | 97.57 | 97.7 | |
| DirPredBackbone=Baichuan-M22026.05 | 97.47 | 97.9 | |
| DirPredBackbone=Gemini 2.5 Pro2026.05 | 97.46 | 97.3 | |
| DirPredBackbone=Claude 3.7 Sonnet2026.05 | 97.38 | 97.2 | |
| DirPredBackbone=GPT-4o2026.05 | 97.36 | 97.2 | |
| COTCAgentBackbone=Qwen3-Next-80B-A3B2026.05 | 97.09 | 97.1 | |
| TimeCAPBackbone=Baichuan-M22026.05 | 97.07 | 96.9 | |
| TimeCAPBackbone=Gemini 2.5 Pro2026.05 | 97.06 | 97.1 | |
| TimeCAPBackbone=GPT-4o2026.05 | 96.96 | 96.9 | |
| TimeCAPBackbone=Claude 3.7 Sonnet2026.05 | 96.94 | 97 | |
| API toolsBackbone=Qwen3-Next-80B-A3B2026.05 | 96.61 | 96.7 | |
| KAREBackbone=Qwen3-Next-80B-A3B2026.05 | 96.47 | 96.8 | |
| Google'sBackbone=Qwen3-Next-80B-A3B2026.05 | 96.24 | 96.1 | |
| DirPredBackbone=Qwen3-Next-80B-A3B2026.05 | 95.97 | 95.7 | |
| TimeCAPBackbone=Qwen3-Next-80B-A3B2026.05 | 95.58 | 94.8 |