Multi-Image Understanding on MMIU 106 (test)
72.1ScoreGemini 3 Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini 3 ProModel Category=API call only2026.01 | 72.1 | |
| GPT-5Model Category=API call only2026.01 | 71 | |
| Gemini 2.5 ProModel Category=API call only2026.01 | 68.9 | |
| GPT-5 miniModel Category=API call only2026.01 | 64.5 | |
| GLM-4.1V-9BModel Category=Open weights only2026.01 | 62.4 | |
| Gemini 2.5 FlashModel Category=API call only2026.01 | 61.2 | |
| Molmo2-4BModel Category=Molmo2 family2026.01 | 55.5 | |
| Molmo2-8BModel Category=Molmo2 family2026.01 | 54.2 | |
| Claude Sonnet 4.5Model Category=API call only2026.01 | 54.1 | |
| Molmo2-O-7BModel Category=Molmo2 family2026.01 | 51.7 | |
| Keye-VL-1.5-8BModel Category=Open weights only2026.01 | 50.3 | |
| InternVL3.5-8BModel Category=Open weights only2026.01 | 49.4 | |
| InternVL3.5-4BModel Category=Open weights only2026.01 | 49.2 | |
| Eagle2.5-8BModel Category=Open weights only2026.01 | 48.4 | |
| MiniCPM-V-4.5-8BModel Category=Open weights only2026.01 | 46.5 | |
| Qwen3-VL-4BModel Category=Open weights only2026.01 | 43.2 | |
| PLM-3BModel Category=Open models2026.01 | 40.6 | |
| Qwen3-VL-8BModel Category=Open weights only2026.01 | 35.3 | |
| PLM-8BModel Category=Open models2026.01 | 27.4 |