List your company

Coding on SWE-bench Multilingual

77.5ScoreClaude Opus 4.5
63.25266.95170.6574.349Feb 17, 2026Mar 11, 2026Apr 2, 2026Apr 24, 2026May 16, 2026Jun 7, 2026Jun 30, 2026

Evaluation results

MethodLinks
Claude Opus 4.5Framework=OpenHands2026.0277.5
GLM-5Framework=OpenHands2026.0273.3
Kimi K2.5Framework=OpenHands2026.0273
GPT-5.2 (xhigh)Framework=OpenHands2026.0272
Gemini-3-Flash High2026.0671.1
DeepSeek-V3.2Framework=OpenHands2026.0270.2
GLM-4.7Framework=OpenHands2026.0266.7
Gemini 3 ProFramework=OpenHands2026.0265
Seed2.0 Lite2026.0664.4
GPT-5-mini High2026.0663.8