# SWE-bench Multimodal 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://modelchoice.dev/leaderboards/benchmarks/multimodal-grounded-swe-multimodal

Every model the catalog carries a published SWE-bench Multimodal value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multimodal & Grounded |
| Measure | Code patch generation with visual context |
| Tasks | Multimodal software engineering tasks |
| Difficulty | Frontier multimodal coding |
| Published by | [SWE-bench Multimodal](https://www.swebench.com/multimodal) |

A multimodal variant of SWE-bench that adds visual context (screenshots, design mockups) to software engineering issue descriptions, testing whether models can leverage visual information for code generation.

## SWE-bench Multimodal ranking

1 model with a published SWE-bench Multimodal 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 | Code patch generation with visual context | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Mythos 5](https://modelchoice.dev/models/claude-mythos-5) | Anthropic | 54.9 | 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.
