Skip to main content
Evaluation sources/SWE-Atlas Refactoring
ObservingCoding

SWE-Atlas Refactoring

Scale AI · Public model evaluation results from SWE-Atlas Refactoring.

Official evaluation
Source description

This source measures concrete delivery performance in Coding; raw scores are shown separately from the normalized capability score.

Limitation: Different versions, reasoning settings, and test sets may change scores; read them with the data date.

How it is used

Participating sources affect capability scores; reference, cross-reference, and observing sources are for comparison and verification only.

Model results from this source

Claude Opus 4.748.5748.62026-08-05
GPT-5.544.7944.82026-08-05
GPT-5.444.2944.32026-08-05
Claude Opus 4.635.5835.62026-08-05
Gemini 3.1 Pro Preview33.8133.82026-08-05
Claude Sonnet 4.632.2132.22026-08-05
GLM-524.2424.22026-08-05
Kimi K2.520.9520.92026-08-05
MiniMax-M2.519.5219.52026-08-05
Gemini 3 Flash Preview1010.02026-08-05

Frequently asked questions