# MMSearch-Plus

> A harder MMSearch variant for multimodal retrieval and grounded tool-use workflows.

Canonical page: https://benchlm.ai/benchmarks/mmsearchplus

- Category: [Multimodal & Grounded](/multimodal-grounded)
- Last updated: September 27, 2026

## About MMSearch-Plus

- Year: 2026
- Tasks: Hard multimodal search tasks
- Format: Advanced mixed-media retrieval benchmark
- Difficulty: Advanced multimodal search
- Paper: [GLM-5V-Turbo](https://docs.z.ai/guides/vlm/glm-5v-turbo)

BenchLM tracks MMSearch-Plus as a display-only extension of multimodal search capability.

MMSearch-Plus is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (1 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Qwen3.7 Plus](/models/qwen3-7-plus) | Alibaba | 41.4% |

## FAQ

### What does MMSearch-Plus measure?

A harder MMSearch variant for multimodal retrieval and grounded tool-use workflows.

### Which model scores highest on MMSearch-Plus?

Qwen3.7 Plus by Alibaba currently leads with a score of 41.4% on MMSearch-Plus.

### How many models are evaluated on MMSearch-Plus?

1 AI models have been evaluated on MMSearch-Plus on BenchLM.

### Does MMSearch-Plus affect BenchLM's overall score?

Not directly. MMSearch-Plus is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.