List your company

Software Engineering on SWE-Bench Verified (Pass@K)

84Pass@1Mini-SWE
19.5236.265369.74Dec 11, 2025Dec 20, 2025Dec 29, 2025Jan 7, 2026Jan 16, 2026Jan 25, 2026Feb 3, 2026

Evaluation results

MethodLinks
Mini-SWEModel Setup=DeepSeek-V3.22026.02848954.76
AORCHESTRAModel Setup=Gemini-3-Flash2026.02828671.62
AORCHESTRAModel Setup=DeepSeek-V3.22026.02768258.43
CCABackbone Model=Claude 4 Sonnet, Scaffold=CCA2025.1274.6——
OpenHandsBackbone Model=Claude 4 Sonnet, Scaffold=OpenHands2025.1272.8——
mini-SWE-AgentBackbone Model=Claude 4.5 Sonnet, Scaffold=mini-SWE-Agent2025.1270.6——
AORCHESTRAModel Setup=Claude-4.5-haiku2026.02708455.44
OpenHandsModel Setup=Claude-4.5-haiku2026.02688345.13
SWE-AgentBackbone Model=Claude 4 Sonnet, Scaffold=SWE-Agent2025.1266.6——
ReActModel Setup=Gemini-3-Flash2026.02648247.22
ReActModel Setup=Claude-4.5-haiku2026.02638743.62
OpenHandsModel Setup=DeepSeek-V3.22026.02607548.35
Mini-SWEModel Setup=Gemini-3-Flash2026.02568549.49
ReActModel Setup=DeepSeek-V3.22026.02488738.23
OpenHandsModel Setup=Gemini-3-Flash2026.02486648.49
Mini-SWEModel Setup=Claude-4.5-haiku2026.02448336.3
Claude CodeModel Setup=Claude-4.5-haiku2026.02254129.65
Claude CodeModel Setup=Gemini-3-Flash2026.02224227.43
AgentKB#Memories=5,8992026.04—72—
MTL#Memories=4312026.04—77—
ReasoningBank#Memories=972026.04—75—
Zeroshot#Memories=-2026.04—73—