MStar
We show this table for reference; we do not rank on it.
A general visual question-answering benchmark used in provider tables for real-image reasoning quality.
Benchmark score on MStar — September 27, 2026
We compile the MStar rows from provider self-reports. Qwen3.6-27B leads the table at 81.4%. We do not use these results to rank models overall.
1 modelMultimodal & GroundedCurrentDisplay onlyUpdated September 27, 2026
Benchmark score table (1 model)
ScoreAbout MStar
Year
2026
Tasks
Real-image visual QA
Format
Image-grounded QA
Difficulty
General visual reasoning
MStar sits between broad multimodal reasoning and grounded VQA. It is useful for checking whether a model can answer real-image questions without the stronger domain structure of office or academic benchmarks.
Freshness and provenance
Version
MStar 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does MStar measure?
A general visual question-answering benchmark used in provider tables for real-image reasoning quality.
Which model scores highest on MStar?
Qwen3.6-27B by Alibaba currently leads with a score of 81.4% on MStar.
How many models are evaluated on MStar?
1 AI models have been evaluated on MStar on BenchLM.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.