reasoning benchmark
SWE-bench Verified (Agentic Coding) Leaderboard
SWE-bench Verified (Agentic Coding) is a human-filtered subset of 500 software engineering problems drawn from real GitHub issues across 12 popular Python repositories.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
SWE-bench Verified (Agentic Coding) Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score77.20% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelMA | Score65.80% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
SWE-bench Verified (Agentic Coding) Highlights
The leading models and scores on this benchmark.
SWE-bench Verified (Agentic Coding) Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for SWE-bench Verified (Agentic Coding)
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is SWE-bench Verified (Agentic Coding)?
What SWE-bench Verified (Agentic Coding) measures and how its scores work.
SWE-bench Verified (Agentic Coding) is a benchmark in which language models generate patches to resolve described problems in provided codebases.
It measures AI's agentic coding skills in navigating codebases, understanding software engineering problems, and coordinating changes across multiple functions, classes, and files to fix well-defined issues, using Score reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- SWE-bench Verified (Agentic Coding)
- Modality
- text
- Primary category
- reasoning
- 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-bench Verified (Agentic Coding).
Which model scores highest on SWE-bench Verified (Agentic Coding)?
Claude Sonnet 4.5 is currently ranked first with 77.20%.
What are the top three models on SWE-bench Verified (Agentic Coding)?
The current leaders are Claude Sonnet 4.5 (77.20%) and Kimi K2 Instruct (65.80%).
Which SWE-bench Verified (Agentic Coding) model has the lowest official input price?
Claude Sonnet 4.5 has the lowest matched official input price at $3.0 input / $15 output per 1M tokens.
Which models are fastest among SWE-bench Verified (Agentic Coding) results?
The fastest matched records are Claude Sonnet 4.5 (42.00 tok/s via Anthropic).
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.