Clinical Report Generation on CheXpert Plus
4.91AccuracyEviAgent
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| EviAgent2026.03 | 4.91 | 6.66 | 8.45 | 5.72 | |
| GPT-5.12026.03 | 4.85 | 4.23 | 8.17 | 5.55 | |
| Lingshu-7BParameters=7B2026.03 | 4.6 | 3.91 | 7.75 | 5.2 | |
| Gemini-2.5-Flash2026.03 | 4.28 | 4.7 | 7.88 | 5.05 | |
| MedGemma-4B-ITParameters=4B2026.03 | 4.16 | 3.82 | 7.68 | 4.8 | |
| Qwen3-VL-8BParameters=8B2026.03 | 3.72 | 3.78 | 7.48 | 4.58 | |
| Claude 4.5 Sonnet2026.03 | 3.41 | 3.14 | 8.3 | 4.33 | |
| InternVL3-8BParameters=8B2026.03 | 2.82 | 3.88 | 7.29 | 3.85 | |
| InternVL2.5-8BParameters=8B2026.03 | 2.55 | 2.86 | 7.06 | 3.52 | |
| Qwen2.5-VL-7BParameters=7B2026.03 | 2.21 | 2.93 | 7.13 | 3.33 | |
| HuatuoGPT-V-7BParameters=7B2026.03 | 1.94 | 4.27 | 5.65 | 2.84 | |
| LLaVA-Med-7BParameters=7B2026.03 | 1.71 | 2.85 | 3.86 | 2.06 | |
| BiMediX2-8BParameters=8B2026.03 | 1.22 | 2.35 | 3.69 | 1.68 |