Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agent on SWE-bench Verified
Loading...
72.8
Accuracy
GLM-5
20.072
33.761
47.45
61.139
Dec 30, 2025
Jan 28, 2026
Feb 26, 2026
Mar 27, 2026
Apr 25, 2026
May 24, 2026
Jun 23, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
GLM-5
Scale Band=Frontier, A...
2026.06
72.8
DeepSeek V3.2
Evaluation Mode=Chat
2025.12
72.1
GLM 4.6
Evaluation Mode=Chat
2025.12
68
LongCat-Flash Exp-Chat
Evaluation Mode=Chat
2025.12
63.2
LongCat-Flash Chat
Evaluation Mode=Chat
2025.12
60.4
OpenThinkerAgent-32B
Scale Band=32B, Agent...
2026.06
54
SWE-Lego-Qwen3-8B
Scale Band=8B, Agent H...
2026.06
37.6
SERA-8B
Scale Band=8B, Agent H...
2026.06
31.5
Nemotron-Terminal-8B
Scale Band=8B, Agent H...
2026.06
22.1
Feedback
Search any
task
Search any
task