multimodal benchmark
MMSearch
MMSearch evaluates multimodal models on search-based retrieval and question answering tasks that require processing both visual and textual information from search results.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
MMSearch Ranking
Higher score ranks better on this benchmark.
| 1 | ZA | 72.9% | 100.0% | 1 | C |
MMSearch Highlights
The leading models and scores on this benchmark.
What is MMSearch?
What MMSearch measures and how its scores work.
MMSearch evaluates multimodal models on search-based retrieval and question answering tasks that require processing both visual and textual information from search results.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MMSearch
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mmsearch|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MMSearch.
Which model scores highest on MMSearch?
GLM-5V-Turbo is currently ranked first with 72.9%.
What does MMSearch measure?
MMSearch evaluates multimodal models on search-based retrieval and question answering tasks that require processing both visual and textual information from search results.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.