Visual Question Answering on InfoQA (test)
83.1AccuracyQwen3-VL-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-VL-8BAccess=Open weights only2026.03 | 83.1 | |
| GPT-5Access=API call only2026.03 | 83 | |
| MolmoPoint-8BAccess=MolmoPoint2026.03 | 83 | |
| GPT-5 miniAccess=API call only2026.03 | 82.2 | |
| Gemini 2.5 ProAccess=API call only2026.03 | 82 | |
| Gemini 2.5 FlashAccess=API call only2026.03 | 80.9 | |
| Eagle2.5-8BAccess=Open weights only2026.03 | 80.4 | |
| Qwen3-VL-4BAccess=Open weights only2026.03 | 80.3 | |
| GLM-4.1V-9BAccess=Open weights only2026.03 | 80.3 | |
| Molmo2-8BAccess=Fully open2026.03 | 80.1 | |
| PLM-8BAccess=Fully open2026.03 | 80 | |
| InternVL3.5-8BAccess=Open weights only2026.03 | 79.1 | |
| Molmo2-4BAccess=Fully open2026.03 | 78.6 | |
| InternVL3.5-4BAccess=Open weights only2026.03 | 78 | |
| MolmoPoint-8B-O-7BAccess=Fully open2026.03 | 77.9 | |
| Keye-VL-1.5-8BAccess=Open weights only2026.03 | 74.9 | |
| PLM-3BAccess=Fully open2026.03 | 74.6 | |
| MiniCPM-V-4.5-8BAccess=Open weights only2026.03 | 73.4 | |
| Claude Sonnet 4.5Access=API call only2026.03 | 65.9 |