Multimodal Understanding on Benchmark Agent 1.0 (test)
72.19Medical AccuracyGemini-3-Pro
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Gemini-3-ProAccess=Commercial Models2026.06 | 72.19 | 82.51 | 67.55 | 72.01 | 90.12 | 88.19 | 80.86 | 80.98 | |
| Qwen3-VL-8BAccess=Open-Source MLLMs2026.06 | 70.74 | 68.53 | 51.06 | 66.67 | 88.94 | 76.97 | 60.96 | 72.14 | |
| GPT-5.2Access=Commercial Models2026.06 | 70.13 | 64.12 | 68.62 | 74.23 | 90.12 | 82.1 | 80.86 | 76.93 | |
| Qwen3-VL-32BAccess=Open-Source MLLMs2026.06 | 69.26 | 72.03 | 64.89 | 69.05 | 94.97 | 84.83 | 70.61 | 76.79 | |
| InternVL3.5-8BAccess=Open-Source MLLMs2026.06 | 66.67 | 30.77 | 21.48 | 56.19 | 82.91 | 79.78 | 65.79 | 63.69 | |
| InternVL3.5-4BAccess=Open-Source MLLMs2026.06 | 64.07 | 27.97 | 16.52 | 50.48 | 80.4 | 69.1 | 60.09 | 58.69 | |
| Qwen2.5-VL-32BAccess=Open-Source MLLMs2026.06 | 63.33 | 68.53 | 57.45 | 67.62 | 88.94 | 79.78 | 71.05 | 73.21 | |
| Qwen3-VL-4BAccess=Open-Source MLLMs2026.06 | 60.37 | 58.74 | 48.4 | 71.43 | 84.42 | 75.28 | 64.04 | 69.05 | |
| Qwen2.5-VL-7BAccess=Open-Source MLLMs2026.06 | 52.22 | 58.04 | 48.94 | 70.48 | 84.92 | 67.42 | 54.82 | 64.65 | |
| Qwen2.5-VL-3BAccess=Open-Source MLLMs2026.06 | 50.74 | 34.27 | 42.55 | 65.71 | 69.35 | 47.19 | 48.68 | 52.66 | |
| LLaVA-OneVision-1.5-4BAccess=Fully Open-Source MLLMs2026.06 | 44.44 | 23.08 | 19.83 | 21.9 | 50.25 | 39.33 | 51.32 | 38.39 | |
| LLaVA-OneVision-1.5-8BAccess=Fully Open-Source MLLMs2026.06 | 42.96 | 12.59 | 13.22 | 19.52 | 57.29 | 43.13 | 56.14 | 38.6 |