multimodal benchmark
MMSearch-Plus Leaderboard
MMSearch-Plus is an extended variant of MMSearch featuring harder multimodal search and retrieval tasks requiring deeper reasoning over visual and textual search results.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
MMSearch-Plus Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score41.40% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelZA | Score30.00% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
MMSearch-Plus Highlights
The leading models and scores on this benchmark.
MMSearch-Plus Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MMSearch-Plus
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is MMSearch-Plus?
What MMSearch-Plus measures and how its scores work.
MMSearch-Plus is a multimodal benchmark for search and retrieval tasks involving visual and textual search results.
It measures performance 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
- MMSearch-Plus
- 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 MMSearch-Plus.
Which model scores highest on MMSearch-Plus?
Qwen3.7-Plus is currently ranked first with 41.40%.
What are the top three models on MMSearch-Plus?
The current leaders are Qwen3.7-Plus (41.40%) and GLM-5V-Turbo (30.00%).
Which MMSearch-Plus model has the lowest official input price?
Qwen3.7-Plus has the lowest matched official input price at $0.50 input / $3.0 output per 1M tokens.
Which models are fastest among MMSearch-Plus results?
No matched runtime record is currently available.
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.