multimodal benchmark
MuirBench Leaderboard
MuirBench is a multimodal benchmark for evaluating multi-image understanding across 12 tasks covering 10 categories of multi-image relations.
Updated Sep 5, 2026
Models12
Model coverage12
MetricScore
EvidenceB
MuirBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score80.30% | Percentile100.00% | Participants12 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score80.10% | Percentile90.91% | Participants12 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score77.60% | Percentile81.82% | Participants12 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score76.80% | Percentile72.73% | Participants12 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score75.00% | Percentile63.64% | Participants12 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score72.80% | Percentile54.55% | Participants12 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score72.80% | Percentile45.45% | Participants12 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score64.40% | Percentile36.36% | Participants12 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score63.80% | Percentile27.27% | Participants12 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score62.90% | Percentile18.18% | Participants12 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score59.20% | Percentile9.09% | Participants12 | EvidenceC | Evaluated |
| Rank12 | ModelLA | Score58.30% | Percentile0.00% | Participants12 | EvidenceC | Evaluated |
MuirBench Highlights
The leading models and scores on this benchmark.
MuirBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MuirBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is MuirBench?
What MuirBench measures and how its scores work.
MuirBench consists of 11,264 images and 2,600 multiple-choice questions created in a pairwise manner, with each standard instance paired with an unanswerable variant.
It measures multi-image understanding capabilities using the Score metric, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MuirBench
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MuirBench.
Which model scores highest on MuirBench?
Qwen3 VL 32B Thinking is currently ranked first with 80.30%.
What are the top three models on MuirBench?
The current leaders are Qwen3 VL 32B Thinking (80.30%), Qwen3 VL 235B A22B Thinking (80.10%), and Qwen3 VL 30B A3B Thinking (77.60%).
Which MuirBench model has the lowest official input price?
Qwen2.5-Omni-7B has the lowest matched official input price at $0.10 input / $0.40 output per 1M tokens.
Which models are fastest among MuirBench results?
The fastest matched records are Qwen3 VL 4B Thinking (8.77 tok/s via DeepInfra).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.