multimodal benchmark
SWE-Bench Multimodal
SWE-Bench Multimodal extends SWE-Bench to evaluate language models on software engineering tasks that involve visual inputs such as screenshots, UI mockups, and diagrams alongside code understanding.
Updated Aug 7, 2026
Published models3
Registry coverage3
MetricScore
EvidenceB
SWE-Bench Multimodal leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AN | 59.0% | 100.0% | 3 | C | |
| 2 | AN | 38.4% | 50.0% | 3 | C | |
| 3 | AN | 28.1% | 0.0% | 3 | C |
Score distribution
Top published rows on the benchmark's original scale.
SWE-Bench Multimodal highlights
The top published results on this benchmark's own scale.
What is SWE-Bench Multimodal?
Definition and scoring fields from the benchmark registry.
SWE-Bench Multimodal extends SWE-Bench to evaluate language models on software engineering tasks that involve visual inputs such as screenshots, UI mockups, and diagrams alongside code understanding.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- SWE-Bench Multimodal
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- swe-bench-multimodal|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about SWE-Bench Multimodal.
Which model scores highest on SWE-Bench Multimodal?
Claude Mythos Preview is currently ranked first with 59.0%.
What does SWE-Bench Multimodal measure?
SWE-Bench Multimodal extends SWE-Bench to evaluate language models on software engineering tasks that involve visual inputs such as screenshots, UI mockups, and diagrams alongside code understanding.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 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.