Chain-of-Thought Reasoning on TumorCoT
64.22S_FC ScoreGPT-5-Mini
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| GPT-5-MiniModel Category=Commercial Models2026.03 | 64.22 | 66.42 | 55.09 | 61.23 | |
| Gemini2.0-FlashModel Category=Commercial Models2026.03 | 63.1 | 57.69 | 45.12 | 54.28 | |
| TumorChain-7BModel Category=Open-Source Models, Parameters=7B2026.03 | 62.37 | 62.6 | 52.57 | 58.33 | |
| TumorChain-3BModel Category=Open-Source Models, Parameters=3B2026.03 | 61.75 | 49.99 | 35.68 | 47.98 | |
| MiniCPM-V4.5-9BModel Category=Open-Source Models, Parameters=9B2026.03 | 60.51 | 58.52 | 45.44 | 53.89 | |
| Claude3-HaikuModel Category=Commercial Models2026.03 | 59.31 | 43.66 | 30.8 | 43.21 | |
| InternVL-2.5-8BModel Category=Open-Source Models, Parameters=8B2026.03 | 56.66 | 57.92 | 47.05 | 53.19 | |
| Lingshu-7BModel Category=Open-Source Models, Parameters=7B2026.03 | 52.51 | 31.93 | 16.46 | 31.92 | |
| HealthGPT-3.8BModel Category=Open-Source Models, Parameters=3.8B2026.03 | 49.64 | 49.68 | 37.15 | 44.65 | |
| Qwen2.5-VL-7BModel Category=Open-Source Models, Parameters=7B2026.03 | 49.15 | 22.89 | 12.09 | 26.45 | |
| MedVLM-R1-2BModel Category=Open-Source Models, Parameters=2B2026.03 | 40.25 | 36.05 | 21.23 | 31.38 |