General perception on MMBench
87.5ScoreSegAnswer
Evaluation results
| Method | Links | |
|---|---|---|
| SegAnswerBase Model=Qwen2.5-VL-7B2026.07 | 87.5 | |
| DeepEyesEvaluation protocol=Re-evaluated using its official model and evaluation code2026.07 | 85.4 | |
| Pixel ReasonerEvaluation protocol=Re-evaluated using its official model and evaluation code2026.07 | 84.7 | |
| Qwen2.5-VL-7BEvaluation protocol=Re-evaluated using its official model and evaluation code2026.07 | 83 | |
| LLaVA-OneVision-9BEvaluation protocol=Re-evaluated using its official model and evaluation code2026.07 | 81.8 |