Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Software Engineering Task Resolution on SWE-BENCH LIVE
Loading...
24.7
Resolution Rate
Qwen3-Coder 480B/A35B Instruct
9.412
13.381
17.35
21.319
Dec 29, 2025
Resolution Rate
Updated 5mo ago
Evaluation Results
Method
Method
Links
Resolution Rate
Qwen3-Coder 480B/A35B Instruct
Scale=Large, Scaffold=...
2025.12
24.7
Seed-OSS-36B-Instruct
Scale=Small, Scaffold=...
2025.12
20
GLM-4.5-Air
Scale=Large, Scaffold=...
2025.12
17.7
Qwen3-Coder-30B-A3B-Instruct
Scale=Small, Scaffold=...
2025.12
17
Seed-OSS-36B-Instruct
Scale=Small, Scaffold=...
2025.12
17
Seed-OSS-36B-Instruct
Scale=Small, Scaffold=...
2025.12
14
Claude 3.7 Sonnet
Scale=Large, Scaffold=...
2025.12
13.7
DeepSeek-V3
Scale=Large, Scaffold=...
2025.12
13.3
Seed-OSS-36B-Instruct
Scale=Small, Scaffold=...
2025.12
12.3
GPT-4o
Scale=Large, Scaffold=...
2025.12
11.7
GPT-4o
Scale=Large, Scaffold=...
2025.12
10
Feedback
Search any
task
Search any
task