reasoning benchmark
SWE-Bench Verified
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Updated Aug 7, 2026
Published models100
Registry coverage104
MetricScore
EvidenceC
SWE-Bench Verified leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
Score distribution
Top published rows on the benchmark's original scale.
SWE-Bench Verified highlights
The top published results on this benchmark's own scale.
What is SWE-Bench Verified?
Definition and scoring fields from the benchmark registry.
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level C.
- Family
- SWE-Bench Verified
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- swe-bench-verified|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 Verified.
Which model scores highest on SWE-Bench Verified?
Claude Fable 5 is currently ranked first with 95.0%.
What does SWE-Bench Verified measure?
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
100 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.