Clinical Report Generation on IU-Xray
7.48AccuracyEviAgent
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| EviAgent2026.03 | 7.48 | 6.55 | 9.29 | 7.72 | |
| GPT-5.12026.03 | 7.42 | 5.51 | 8.81 | 7.08 | |
| Lingshu-7BParameters=7B2026.03 | 7.39 | 6.24 | 8.88 | 7.67 | |
| MedGemma-4B-ITParameters=4B2026.03 | 7.24 | 6.28 | 8.38 | 7.41 | |
| Claude 4.5 Sonnet2026.03 | 7.12 | 5.6 | 9.15 | 7.2 | |
| InternVL2.5-8BParameters=8B2026.03 | 6.81 | 5.87 | 8 | 6.58 | |
| Gemini-2.5-Flash2026.03 | 6.67 | 5.73 | 8.61 | 6.7 | |
| Qwen2.5-VL-7BParameters=7B2026.03 | 5.79 | 6.04 | 7.86 | 5.91 | |
| Qwen3-VL-8BParameters=8B2026.03 | 5.74 | 4.98 | 7.63 | 5.64 | |
| InternVL3-8BParameters=8B2026.03 | 3.68 | 6.36 | 7.72 | 4.48 | |
| LLaVA-Med-7BParameters=7B2026.03 | 2.07 | 3.37 | 3.86 | 2.01 | |
| HuatuoGPT-V-7BParameters=7B2026.03 | 1.21 | 5.5 | 5.95 | 2.29 | |
| BiMediX2-8BParameters=8B2026.03 | 0.51 | 2.77 | 4.27 | 1.14 |