Verified AI Benchmarks • Updated September 2026

SWE-bench Pro Explained

What SWE-bench Pro measures, how it differs from SWE-bench Verified, why contamination resistance matters, and which models lead agentic coding today.

SWE-bench Pro is the harder successor to SWE-bench Verified, the benchmark that measures whether an AI model can resolve real GitHub issues end to end. While SWE-bench Verified made agentic coding famous, its public tasks became a victim of the field's success: frontier labs could tune against them, and the score gap between "great at benchmarks" and "great at your codebase" kept growing. SWE-bench Pro exists to close that gap with harder tasks and contamination resistance.

What SWE-bench Pro Actually Tests

Like the original, each task gives the model a repository and an issue description, and the model must produce a patch that passes the repository's hidden tests. SWE-bench Pro raises the difficulty in three ways:

  • Larger, messier repositories. Tasks draw on bigger, more realistic codebases - including commercial and enterprise code - where the fix requires understanding code far from the issue's symptoms.
  • Multi-file, multi-step changes. Many tasks require coordinated edits across several files, not the single-function patches that dominated the original benchmark.
  • Contamination resistance. Held-out private tasks mean a model cannot score well by having memorized public test cases during training, which makes cross-lab comparisons more honest over time.

SWE-bench Verified vs SWE-bench Pro

SWE-bench VerifiedSWE-bench Pro
Human-validated subset of public GitHub issuesHarder split with private holdout tasks
Mostly single-repo, well-scoped issuesCommercial-grade repos, multi-file fixes
Risk of training-data contaminationDesigned to resist memorization
Scores in the 30-50% range defined the 2024 frontierSubstantially lower scores at the same capability level

The practical rule: a 49% SWE-bench Verified score (Claude 3.5 Sonnet's famous October 2024 result - see our historical breakdown) and a 30% SWE-bench Pro score are not comparable numbers. Within one benchmark version, comparisons are meaningful; across versions, they are not.

Who Leads Agentic Coding Right Now

The table below is from the RankLLMs dataset (last verified September 2026): SWE-bench Verified accuracy and Terminal Bench performance for the current agentic coding leaders, with blended per-million-token API pricing. Full rankings and pillars are on the leaderboard.

ModelProviderSWE-bench VerifiedTerminal BenchAPI $/1M
Claude Fable 5Anthropic84.588.0$14.44
Claude Opus 5Anthropic81.885.4$7.22
GPT-5.6 SolOpenAI81.288.8$7.78
DeepSeek-V4-Pro-0813DeepSeek81.080.3$1.74 / $3.48
Kimi K3Moonshot AI80.585.7$4.33
Qwen3.8 MaxAlibaba Qwen79.486.6$2.02
Gemini 3.7 FlashGoogle78.685.8$0.75 / $3.75
GLM-5.3Z.ai77.888.3$1.73

Scores per the RankLLMs composite dataset; see our methodology for sources and verification dates.

How to Use SWE-bench Pro Scores When Choosing a Model

  • Compare within the same harness. Agentic scores depend on scaffolding and step budgets; only compare runs with published evaluation details.
  • Weight cost per solved task, not per token. A cheaper model that retries twice can cost more than an expensive one that lands the fix first - our best coding LLM guide does this math.
  • Prefer contamination-resistant results for trend claims. For "is the new release actually better," Pro-style held-out results are the ones to trust.