Document Visual Question Answering on InfoQA 105 (test)
86.9ScoreGemini 3 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 3 ProModel Category=API call only2026.01 | 86.9 | |
| Qwen3-VL-8BModel Category=Open weights only2026.01 | 83.1 | |
| GPT-5Model Category=API call only2026.01 | 83 | |
| GPT-5 miniModel Category=API call only2026.01 | 82.2 | |
| Gemini 2.5 ProModel Category=API call only2026.01 | 82 | |
| Molmo-72BModel Category=Molmo1 family2026.01 | 81.9 | |
| Gemini 2.5 FlashModel Category=API call only2026.01 | 80.9 | |
| Eagle2.5-8BModel Category=Open weights only2026.01 | 80.4 | |
| Qwen3-VL-4BModel Category=Open weights only2026.01 | 80.3 | |
| GLM-4.1V-9BModel Category=Open weights only2026.01 | 80.3 | |
| Molmo2-8BModel Category=Molmo2 family2026.01 | 80.1 | |
| PLM-8BModel Category=Open models2026.01 | 80 | |
| InternVL3.5-8BModel Category=Open weights only2026.01 | 79.1 | |
| Molmo2-4BModel Category=Molmo2 family2026.01 | 78.6 | |
| InternVL3.5-4BModel Category=Open weights only2026.01 | 78 | |
| Molmo2-O-7BModel Category=Molmo2 family2026.01 | 77.9 | |
| Keye-VL-1.5-8BModel Category=Open weights only2026.01 | 74.9 | |
| PLM-3BModel Category=Open models2026.01 | 74.6 | |
| MiniCPM-V-4.5-8BModel Category=Open weights only2026.01 | 73.4 | |
| Molmo-7B-DModel Category=Molmo1 family2026.01 | 72.6 | |
| Molmo-7B-OModel Category=Molmo1 family2026.01 | 70 | |
| Claude Sonnet 4.5Model Category=API call only2026.01 | 65.9 | |
| MolmoE-1BModel Category=Molmo1 family2026.01 | 53.9 |