OpenGPTEvidence-based model decisionsAgent configuration · SWE-bench Verified
mini-SWE-agent + Claude 4.5 Opus (high reasoning)
The ranked object: model, scaffold, tools, permissions, budget, and environment together.
System identity
Agent systemmini-SWE-agent + Claude 4.5 Opus (high reasoning)
Base modelClaude 4.5 Opus (high reasoning)
Source model ID or labelclaude-4-5-opus
Scaffoldmini-SWE-agent
Scaffold version2.0.0
ToolsMinimal repository shell
Comparability groupswe-bench-verified-full-500
Evaluation configuration
Source snapshotSWE-bench Verified · Verified · Full leaderboard · 500 tasks · Jul 30, 2026
Tasks500 human-validated GitHub issues
EnvironmentReproducible repository environments evaluated by SWE-bench
BudgetLimits vary by submitted configuration
Evaluation date
Data captured
Resolved76.8%
Partial scoreNot reported
Published evidence
Open sourceEvidenceListed by the benchmark publisher
SourceSWE-bench Verified
Cost$376.95
Cost basisTotal benchmark cost reported by the source
What this result does not prove
This result applies to the exact system and source conditions shown here. It does not establish a universal best agent, production reliability, data governance, or performance on a different benchmark version.