Vision-Centric Understanding on RealworldQA
75.4AccuracyGPT4o
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT4oModel Category=Proprietary Model2025.09 | 75.4 | |
| VisionZero-Qwen-7B (CLEVR)Base Model=Qwen2.5-VL-7B, Variant=CLEVR2025.09 | 68.5 | |
| VisionZero-Qwen-7B (Real-World)Base Model=Qwen2.5-VL-7B, Variant=Real-World2025.09 | 68.5 | |
| VisionZero-Qwen-7B (Chart)Base Model=Qwen2.5-VL-7B, Variant=Chart2025.09 | 68.2 | |
| Qwen2.5-VL-7B-InstructBase Model=Qwen2.5-VL-7B2025.09 | 68.1 | |
| ViGaL-Snake+RotationBase Model=Qwen2.5-VL-7B2025.09 | 66.5 | |
| MM-Eureka-Qwen-7BBase Model=Qwen2.5-VL-7B2025.09 | 66.1 | |
| VLAA-Thinker-7BBase Model=Qwen2.5-VL-7B2025.09 | 65.4 | |
| OpenVLThinker-7BBase Model=Qwen2.5-VL-7B2025.09 | 60.2 | |
| R1-OneVision-7BBase Model=Qwen2.5-VL-7B2025.09 | 58 |