General VQA on GUIChat
93.14AccuracyClaude 4 sonnet
Evaluation results
| Method | Links | |
|---|---|---|
| Claude 4 sonnetModel Category=Closed-Source Models2026.01 | 93.14 | |
| Qwen 2.5 VL 72BModel Category=Open-Source Models, Backbone=72B2026.01 | 88.01 | |
| Qwen 2.5 VL 32BModel Category=Open-Source Models, Backbone=32B2026.01 | 85.21 | |
| Gemini 2.5 flashModel Category=Closed-Source Models2026.01 | 83.05 | |
| InternVL3 78BModel Category=Open-Source Models, Backbone=78B2026.01 | 79.83 | |
| Qwen 2.5 VL 72B + ToolsModel Category=Tool-Planning Models, Tool Usage=true, Backbone=72B2026.01 | 77.13 | |
| GPT 5 + ToolsModel Category=Tool-Planning Models, Tool Usage=true2026.01 | 76.51 | |
| AdaReasoner 7BModel Category=Tool-Planning Models, Backbone=7B2026.01 | 73.91 | |
| PixelReasonerModel Category=Tool-Planning Models, Unified Evaluation Framework=true2026.01 | 72.45 | |
| GPT 5Model Category=Closed-Source Models2026.01 | 71.41 | |
| Qwen 2.5 VL 7BModel Category=Open-Source Models, Backbone=7B2026.01 | 68.09 | |
| DeepEyesModel Category=Tool-Planning Models, Unified Evaluation Framework=true2026.01 | 65.9 | |
| Qwen 2.5 VL 7B + ToolsModel Category=Tool-Planning Models, Tool Usage=true, Backbone=7B2026.01 | 56.76 | |
| Qwen 2.5 VL 3BModel Category=Open-Source Models, Backbone=3B2026.01 | 46.26 |