multimodal benchmark
MMSearch-Plus
MMSearch-Plus is an extended variant of MMSearch with harder multimodal search and retrieval tasks requiring deeper reasoning over visual and textual search results.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
MMSearch-Plus leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 41.4% | 100.0% | 2 | C | |
| 2 | ZA | 30.0% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
MMSearch-Plus highlights
The top published results on this benchmark's own scale.
What is MMSearch-Plus?
Definition and scoring fields from the benchmark registry.
MMSearch-Plus is an extended variant of MMSearch with harder multimodal search and retrieval tasks requiring deeper reasoning over visual and textual search results.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MMSearch-Plus
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mmsearch-plus|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MMSearch-Plus.
Which model scores highest on MMSearch-Plus?
Qwen3.7-Plus is currently ranked first with 41.4%.
What does MMSearch-Plus measure?
MMSearch-Plus is an extended variant of MMSearch with harder multimodal search and retrieval tasks requiring deeper reasoning over visual and textual search results.
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.