Benchmark
SWE-MM Benchmark
What is SWE-MM?
SWE-MM evaluates software-engineering agents on repository tasks that require understanding both source code and visual evidence.
- Modality
- multimodal
- Evaluates
- multimodal, agents, code, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 1
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/swe-mm?top_n=500
SWE-MM results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen3.8-27B | Qwen | 0.386 | 2026-08-14 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.