List your company

Software Engineering on SWE-Bench-Verified (50 cases)

72AccuracySWE-agent + Claude 3.7 Sonnet w/ Review Heavy
7.5224.264157.74May 16, 2025

Evaluation results

MethodLinks
SWE-agent + Claude 3.7 Sonnet w/ Review HeavyOpen/Close Source=Open Source2025.0572
CodeStory Midwit Agent + swe-searchOpen/Close Source=Close Source2025.0570
Openhands_04_15Open/Close Source=Open Source2025.0568
InfantAgent-Next + Claude-3.7-SonnetOpen/Close Source=Open Source2025.0566
AgentScopeOpen/Close Source=Close Source2025.0566
CORTEXAOpen/Close Source=Close Source2025.0562
Amazon Q Developer Agent_2024_12_02Open/Close Source=Close Source2025.0554
AutoCodeRover-v2.0 (Claude-3.5-Sonnet-20241022)Open/Close Source=Open Source2025.0552
devlo_2024_11_08Open/Close Source=Close Source2025.0548
SWE-agent + SWE-agent-LM-32BOpen/Close Source=Open Source2025.0546
AppMap Navie v2Open/Close Source=Open Source2025.0512
Agentless Lite + O3 Mini (20250214)Open/Close Source=Open Source2025.0510