ReportQA on AMOS-MM
31.25QAScoreClaude Opus 4.6
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude Opus 4.6Category=Proprietary VLMs2026.06 | 31.25 | |
| RadFMCategory=Open-source VLMs (medical)2026.06 | 24.99 | |
| GPT-5.4Category=Proprietary VLMs2026.06 | 21.65 | |
| CT-CHAT (70B)Category=Open-source VLMs (medical), Parameters=70B2026.06 | 17.19 | |
| Hulu-Med-32BCategory=Open-source VLMs (medical), Parameters=32B2026.06 | 12.56 | |
| Gemini 3.1 ProCategory=Proprietary VLMs2026.06 | 8.37 | |
| Qwen3.5-27BCategory=Open-source VLMs (general), Parameters=27B2026.06 | 1.61 | |
| MedGemma 1.5 (4B)Category=Open-source VLMs (medical), Parameters=4B2026.06 | 1.1 | |
| InternVL3.5-38BCategory=Open-source VLMs (general), Parameters=38B2026.06 | 0.03 |