List your company

Software Engineering on SWE-bench Verified 500 issues (Protocol A)

73.6Success Rate (SR)OpenHands CodeAct + GBT-SE
33.0443.5754.164.63Jan 30, 2026

Evaluation results

MethodLinks
OpenHands CodeAct + GBT-SEBackbone=gpt-4o, Protocol=A2026.0173.6860.20126490
OpenHands CodeAct + GBT-BasicBackbone=gpt-4o, Protocol=A2026.0150.284.40.40.2148570
OpenHands CodeAct + Global guardrail onlyBackbone=gpt-4o, Protocol=A2026.0138.8—0.80.2196770
OpenHands CodeAct (gpt-4o, native)Backbone=gpt-4o, Protocol=A2026.0134.6—2.81.2208820