Skip to main content
Evaluation sources/SWE-Bench Multilingual
ObservingChinese & multilingual

SWE-Bench Multilingual

SWE-bench · Public model evaluation results from SWE-Bench Multilingual.

Official evaluation
Source description

This source measures concrete delivery performance in Chinese & multilingual; 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

Ornith 1.0 397B78.978.92026-08-05
Qwen3.7 Max78.378.32026-05-19
Claude Sonnet 578.378.32026-06-30
Grok 4.57878.02026-07-08
LongCat-2.077.377.32026-06-30
Ornith 1.0 35B69.369.32026-08-05
Nemotron 3 Ultra 550B A55B67.767.72026-06-04
Laguna XS 2.163.163.12026-07-02
Ornith 1.0 9B5252.02026-08-05

Frequently asked questions