Question Answering on Pulmonary-QA (test)
4.416ScoreLung-R1-14B
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Lung-R1-14BSize=14B2026.06 | 4.416 | 0.9239 | 81.2 | |
| Gemini-3-ProVariant=Pro2026.06 | 4.396 | 0.846 | 80.8 | |
| Claude-Sonnet-4.5Version=4.52026.06 | 4.396 | 0.9046 | 82.4 | |
| Qwen3-30B-A3BSize=30B2026.06 | 4.292 | 0.863 | 76 | |
| DeepSeek-R1Variant=R12026.06 | 4.264 | 0.8847 | 77.6 | |
| DeepSeek-V3.2Version=3.22026.06 | 4.256 | 0.8394 | 76.4 | |
| GPT-4oVariant=o2026.06 | 4.176 | 0.8611 | 72.8 | |
| GPT-5-chatVariant=chat2026.06 | 4.1551 | 0.9002 | 75.1 | |
| GPT-5.1Version=5.12026.06 | 4.1488 | 0.9182 | 73.14 | |
| GPT-4.1Version=4.12026.06 | 4.132 | 0.8739 | 72.8 | |
| Lung-R1-7BSize=7B2026.06 | 4.12 | 0.9123 | 72.8 | |
| GPT-OSS-120BSize=120B2026.06 | 4.108 | 0.8886 | 73.2 | |
| Baichuan-M2Version=M22026.06 | 4.016 | 0.8822 | 68 | |
| Qwen2.5-14BSize=14B2026.06 | 3.996 | 0.8727 | 68.4 | |
| MedGemma-27BSize=27B2026.06 | 3.792 | 0.8477 | 65.2 | |
| GPT-OSS-20BSize=20B2026.06 | 3.768 | 0.8607 | 65.6 | |
| Qwen2.5-7BSize=7B2026.06 | 3.66 | 0.8863 | 60.4 | |
| HuatuoGPT-o1-7BSize=7B2026.06 | 3.636 | 0.8686 | 58.4 | |
| ClinicalGPT-R1Variant=R12026.06 | 3.588 | 0.8598 | 55.2 | |
| Kimi-K2-ThinkingVariant=Thinking2026.06 | 3.44 | 0.8749 | 52.8 |