SWE-bench Verified (mini-swe-agent-v2) (SWE-bench Verified*)
We show this table for reference; we do not rank on it.
A display-only SWE-bench Verified reference from Arcee AI's Trinity-Large-Thinking comparison chart.
Benchmark score on SWE-bench Verified* — September 27, 2026
We compile the SWE-bench Verified* rows from secondary reports. Claude Opus 4.6 leads the table at 75.6%, followed by MiniMax M2.7 (75.4%) and GLM-5 (72.8%). We do not use these results to rank models overall.
Claude Opus 4.6
Anthropic
MiniMax M2.7
MiniMax
GLM-5
Z.AI
5 modelsCodingCurrentDisplay onlyUpdated September 27, 2026
Benchmark score table (5 models)
ScoreAmong the reported SWE-bench Verified* rows, Claude Opus 4.6 is first at 75.6%. The third row is 2.8 points behind. The broader top-10 range is 12.4 points, so the table still separates the published systems.
5 models have been evaluated on SWE-bench Verified*. The benchmark falls in the Coding category. SWE-bench Verified* is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About SWE-bench Verified*
Year
2026
Tasks
Repository task completion
Format
Agent scaffold benchmark
Difficulty
Professional software engineering
BenchLM stores this chart-specific SWE-bench Verified row separately because Arcee notes all models were evaluated in mini-swe-agent-v2.
Freshness and provenance
Version
SWE-bench Verified* 2026
Refresh cadence
Quarterly
Staleness state
Current
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.
Questions
What does SWE-bench Verified* measure?
A display-only SWE-bench Verified reference from Arcee AI's Trinity-Large-Thinking comparison chart.
Which model scores highest on SWE-bench Verified*?
Claude Opus 4.6 by Anthropic currently leads with a score of 75.6% on SWE-bench Verified*.
How many models are evaluated on SWE-bench Verified*?
5 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.