Benchmark profile
SWE-bench Multimodal (SWE Multimodal)
A multimodal variant of SWE-bench that adds visual context such as screenshots and design mockups to software engineering issue descriptions.
Data verifiedBenchmark score on SWE Multimodal — July 23, 2026
BenchLM mirrors the published score view for SWE Multimodal. Claude Opus 4.8 leads the public snapshot at 38.4% , followed by Claude Sonnet 5 (28.1%). BenchLM does not use these results to rank models overall.
Claude Opus 4.8
Anthropic
claude-opus-4-8
Claude Sonnet 5
Anthropic
claude-sonnet-5
Benchmark score table (2 models)
ScoreAbout SWE Multimodal
Year
2025
Tasks
Multimodal software engineering tasks
Format
Code patch generation with visual context
Difficulty
Frontier multimodal coding
BenchLM stores provider-reported SWE-bench Multimodal values in the coding category when the model vendor reports the benchmark as part of a software-engineering capability suite.
BenchLM freshness & provenance
Version
SWE Multimodal 2025
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
FAQ
What does SWE Multimodal measure?
A multimodal variant of SWE-bench that adds visual context such as screenshots and design mockups to software engineering issue descriptions.
Which model scores highest on SWE Multimodal?
Claude Opus 4.8 by Anthropic currently leads with a score of 38.4% on SWE Multimodal.
How many models are evaluated on SWE Multimodal?
2 AI models have been evaluated on SWE Multimodal on BenchLM.
Compare Top Models on SWE Multimodal
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.