Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Coding on SWE-bench Multilingual
Loading...
77.5
Score
Claude Opus 4.5
63.252
66.951
70.65
74.349
Feb 17, 2026
Mar 11, 2026
Apr 2, 2026
Apr 24, 2026
May 16, 2026
Jun 7, 2026
Jun 30, 2026
Score
Updated 23d ago
Evaluation Results
Method
Method
Links
Score
Claude Opus 4.5
Framework=OpenHands
2026.02
77.5
GLM-5
Framework=OpenHands
2026.02
73.3
Kimi K2.5
Framework=OpenHands
2026.02
73
GPT-5.2 (xhigh)
Framework=OpenHands
2026.02
72
Gemini-3-Flash High
2026.06
71.1
DeepSeek-V3.2
Framework=OpenHands
2026.02
70.2
GLM-4.7
Framework=OpenHands
2026.02
66.7
Gemini 3 Pro
Framework=OpenHands
2026.02
65
Seed2.0 Lite
2026.06
64.4
GPT-5-mini High
2026.06
63.8
Feedback
Search any
task
Search any
task