multimodal benchmark
SWE-MM Leaderboard
SWE-MM evaluates software-engineering agents on repository tasks that require understanding both source code and visual evidence.
Updated Sep 5, 2026
Models1
Model coverage1
MetricScore
EvidenceB
SWE-MM Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score38.60% | Percentile100.00% | Participants1 | EvidenceC | Evaluated |
SWE-MM Highlights
The leading models and scores on this benchmark.
The Top AI Models for SWE-MM
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis swe-mm AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ACAlibaba Cloud / Qwen Team
- Score
- 38.60%
Strengths
- Ranks #1 of 1 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures SWE-MM, not total model capability
Selection summary
Best AI Models for SWE-MM
Qwen3.8-27B currently leads SWE-MM with 38.60%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is SWE-MM?
What SWE-MM measures and how its scores work.
SWE-MM is a multimodal benchmark for evaluating software-engineering agents on repository tasks involving source code and visual evidence.
It measures performance using the Score metric, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- SWE-MM
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about SWE-MM.
Which model scores highest on SWE-MM?
Qwen3.8-27B is currently ranked first with 38.60%.
What are the top three models on SWE-MM?
The current leaders are Qwen3.8-27B (38.60%).
Which SWE-MM model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among SWE-MM results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.