multimodal benchmark
MeasureBench
MeasureBench evaluates multimodal models on visual measurement and quantitative perception tasks across both real and synthetic imagery, reported as the average over the two settings.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
MeasureBench leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | BY | 62.9% | 100.0% | 2 | C | |
| 2 | BY | 58.9% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
MeasureBench highlights
The top published results on this benchmark's own scale.
What is MeasureBench?
Definition and scoring fields from the benchmark registry.
MeasureBench evaluates multimodal models on visual measurement and quantitative perception tasks across both real and synthetic imagery, reported as the average over the two settings.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MeasureBench
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- measurebench|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MeasureBench.
Which model scores highest on MeasureBench?
Seed 2.1 Pro is currently ranked first with 62.9%.
What does MeasureBench measure?
MeasureBench evaluates multimodal models on visual measurement and quantitative perception tasks across both real and synthetic imagery, reported as the average over the two settings.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.