Best LLMs for long-horizon repository fixes

SWE-bench Pro

Tests substantial software repository issues, helping you assess which model could support complex fixes and implementation work for clients. The source does not establish a specific Pro release, so these scores are not labeled v2 Hard.

Updated: Nov 9, 2026Data as of: Nov 9, 2026

Limited reportingSaturated

Official benchmark

SWE-bench Pro results. Each row identifies its benchmark version and evaluation track. Scores from different versions are not directly comparable. Best effort from the latest stored report date per model and version.
Model / creator	Version	Reported score
Claude Fable 5.2Anthropic · Proprietary	Anthropic November 2026 / five trials	93%

View all 1 published reports

Claude Fable 5.293%

Anthropic November 2026 / five trials

effort: max · Mean of five trials; variant as stated in system card. No Verified or version-specific Pro score inferred. · Tools enabled

Anthropic ↗

Sources and original reports ↗

Other benchmarks

LiveBench: Coding

Tests coding tasks, helping you compare models for implementation work that you would otherwise write or debug yourself.

DeepFinance

Tests private equity and investment banking work such as valuation, due diligence and financial modeling, helping you assess AI support for demanding client analysis.

Harvey LAB-AA

Tests whether an agent can produce legal deliverables that meet every requirement without material hallucinations, helping you assess how much drafting and document work you could delegate before professional review.