Skip to main content
Evaluation sources/SWE-Atlas Test Writing
ObservingCoding

SWE-Atlas Test Writing

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

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

GPT-5.444.3644.42026-08-05
GPT-5.542.5942.62026-08-05
GPT-5.44040.02026-08-05
Claude Opus 4.636.6736.72026-08-05
Claude Opus 4.636.0836.12026-08-05
Claude Sonnet 4.631.7631.82026-08-05
Gemini 3 Flash Preview30.330.32026-08-05
Gemini 3.1 Pro Preview29.8429.82026-08-05
GLM-528.7428.72026-08-05
Kimi K2.525.7725.82026-08-05
MiniMax-M2.518.618.62026-08-05

Frequently asked questions