MStar
A general visual question-answering benchmark used in provider tables for real-image reasoning quality.
1 models
Higher is better.
- 1Qwen3.6-27BAlibaba81.4
About this benchmark
- Metric
- Image-grounded QA
- Tasks
- Real-image visual QA
- Authors
- Qwen (2026)
Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.