General VQA on VisuLogic
27.1ScoreSegAnswer
Evaluation results
| Method | Links | |
|---|---|---|
| SegAnswerBase Model=Qwen2.5-VL-7B2026.07 | 27.1 | |
| DeepEyesEvaluation protocol=Re-evaluated using its official model and evaluation code2026.07 | 26.7 | |
| Bee-8BOpenness=fully open, Model Size=8B, Training Strategy=RL2025.10 | 26.5 | |
| Qwen2.5-VL-7BEvaluation protocol=Re-evaluated using its official model and evaluation code2026.07 | 26.1 | |
| Keye-VLOpenness=semi-open, Model Size=8B2025.10 | 25.6 | |
| Pixel ReasonerEvaluation protocol=Re-evaluated using its official model and evaluation code2026.07 | 25.3 | |
| Bee-8BOpenness=fully open, Model Size=8B, Training Strategy=SFT2025.10 | 24.4 | |
| LLaVA-OneVision-9BEvaluation protocol=Re-evaluated using its official model and evaluation code2026.07 | 22.7 | |
| Qwen2.5-VLOpenness=semi-open, Model Size=7B2025.10 | 20 |