SWE-Bench Pro - Commercial

Updated Aug 12, 2026·1,915 views

Problem Count: 276
Institution: Scale AI
Category: Coding and Software Engineering
Metrics: Resolve Rate
Language: English
Difficulty: Advanced

Overview

A commercial benchmark dataset for evaluating whether models can solve realistic, complex software-engineering tasks.

Related resources

Latest SWE-Bench Pro - Commercial model rankings and full benchmark leaderboard

Browse the latest scores, model modes, release dates, and parameter sizes for SWE-Bench Pro - Commercial.

Source: DataLearnerAI

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Model Mode Legend

License:

Origin:

Model release cutoff:

Model				License
Claude Opus 4.6 Thinking EnabledTools	47.10	2026-02-05	Unknown	Closed
GPT-5.4 Thinking Level · Extra HighTools	43.40	2026-03-05	Unknown	Closed
Gemini 3.1 Pro Preview Thinking EnabledTools	32.20	2026-02-20	Unknown	Closed

Latest SWE-Bench Pro - Commercial model rankings and full benchmark leaderboard

SWE-Bench Pro - Commercial Rank