# MMSearch-Plus leaderboard

Multimodal & Grounded benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/multimodal-grounded-mm-search-plus

Every model the catalog carries a published MMSearch-Plus value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multimodal & Grounded |
| Measure | Advanced mixed-media retrieval benchmark |
| Tasks | Hard multimodal search tasks |
| Difficulty | Advanced multimodal search |
| Published by | [GLM-5V-Turbo](https://docs.z.ai/guides/vlm/glm-5v-turbo) |

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

## MMSearch-Plus ranking

1 model with a published MMSearch-Plus value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Advanced mixed-media retrieval benchmark | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Qwen3.7 Plus](https://modelscale.dev/models/qwen3-7-plus) | Alibaba | 41.4 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
