Software Engineering Benchmark Verified (SWE-bench Verified)
A curated, human-verified subset of SWE-bench that tests models on resolving real GitHub issues from popular open-source Python repositories like Django, Flask, and scikit-learn.
Data verified 37 confirmed releases in the last 30 daysSee provider release alertsClaude Opus 5 leads the SWE-bench Verified leaderboard on BenchLM's September 2026 update with 96%, ahead of Claude Mythos 5 (95.5%) and Claude Fable 5 (95%), across 78 models.
Top models on SWE-bench Verified — September 10, 2026
As of September 10, 2026, Claude Opus 5 leads the SWE-bench Verified leaderboard with 96% , followed by Claude Mythos 5 (95.5%) and Claude Fable 5 (95%).
Claude Opus 5
Anthropic
Claude Mythos 5
Anthropic
Claude Fable 5
Anthropic
78 modelsCoding10% of category scoreRefreshingUpdated September 10, 2026
Leaderboard (78 models)
ScoreAccording to BenchLM.ai, Claude Opus 5 leads the SWE-bench Verified benchmark with a score of 96%, followed by Claude Mythos 5 (95.5%) and Claude Fable 5 (95%). The top models are clustered within 1.0 points, suggesting this benchmark is nearing saturation for frontier models.
78 models have been evaluated on SWE-bench Verified. The benchmark falls in the Coding category. This category carries a 20% weight in BenchLM.ai's overall scoring system. Within that category, SWE-bench Verified contributes 10% of the category score, so strong performance here directly affects a model's overall ranking.
About SWE-bench Verified
Year
2024
Tasks
500 verified issues
Format
Code patch generation
Difficulty
Professional software engineering
SWE-bench Verified is the most-cited benchmark for AI coding agents on real repository tasks. Each task requires understanding codebases, writing patches, and passing test suites.
BenchLM freshness & provenance
Version
SWE-bench Verified 2024
Refresh cadence
Annual
Staleness state
Refreshing
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-bench Verified measure?
A curated, human-verified subset of SWE-bench that tests models on resolving real GitHub issues from popular open-source Python repositories like Django, Flask, and scikit-learn.
Which model scores highest on SWE-bench Verified?
Claude Opus 5 by Anthropic currently leads with a score of 96% on SWE-bench Verified.
How many models are evaluated on SWE-bench Verified?
78 AI models have been evaluated on SWE-bench Verified on BenchLM.
Compare Top Models on SWE-bench Verified
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.