Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Software Engineering Issue Resolution on SWE-Bench Lite
Loading...
73.5
Resolution Rate
AIR
7.46
24.605
41.75
58.895
Feb 27, 2025
Apr 15, 2025
Jun 2, 2025
Jul 19, 2025
Sep 5, 2025
Oct 22, 2025
Dec 9, 2025
Resolution Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Resolution Rate
AIR
Backbone=Gemini 2.5
2025.12
73.5
SWE-agent
Backbone=Claude 4 Sonnet
2025.12
56.67
Claude-3.5-Sonnet
Framework=Openhands, T...
2025.02
41.7
Claude-3.5-Sonnet
Framework=Agentless, T...
2025.02
40.7
AutoCodeRover
Backbone=GPT-4o
2025.12
37.3
SWE-agent
Backbone=Claude 3.5 So...
2025.12
33.6
OpenHands
Backbone=Claude 3.5 So...
2025.12
27.7
SoRFT-Qwen-32B
Framework=Agentless, T...
2025.02
24
SWE-Fixer-Qwen-72B
Framework=SWE-Fixer, T...
2025.02
23.3
Lingma-SWE-GPT-72B
Framework=SWE-SynInfer...
2025.02
22
GPT-4o
Framework=SWE-SynInfer...
2025.02
20.7
SWE-Gym-Qwen-32B
Framework=Openhands, T...
2025.02
15.3
SoRFT-Qwen-7B
Framework=Agentless, T...
2025.02
14
SWE-Gym-Qwen-14B
Framework=Openhands, T...
2025.02
12.7
Lingma-SWE-GPT-7B
Framework=SWE-SynInfer...
2025.02
12
SWE-Gym-Qwen-7B
Framework=Openhands, T...
2025.02
10
Feedback
Search any
task
Search any
task