OpenGPTEvidence-based model decisionsAgent configuration · OSWorld 2.0
OSWorld Agent · Qwen 3.7-Plus · Thinking · Standard
The ranked object: model, scaffold, tools, permissions, budget, and environment together.
System identity
Agent systemOSWorld Agent · Qwen 3.7-Plus · Thinking · Standard
Base modelQwen 3.7-Plus
Source model ID or labelQwen 3.7-Plus
ScaffoldOSWorld 2.0 computer-use agent
Scaffold versionOSWorld 2.0
ToolsStandard computer-use tool
Comparability grouposworld-2-v2026-06-24-500
Evaluation configuration
Source snapshotOSWorld 2.0 · Task version v2026.06.24 · 500-step budget · Jun 25, 2026
Tasks108 long-horizon computer workflows
EnvironmentDesktop and operating-system workflows in reproducible virtual machines
Budget500 steps
Evaluation date
Data captured
Binary completion2.8%
Partial score21.5%
Published evidence
Open sourceEvidenceListed by the benchmark publisher
SourceOSWorld 2.0
Cost$411.56
Cost basisTotal benchmark cost reported by the source
What this result does not prove
This result applies to the exact system and source conditions shown here. It does not establish a universal best agent, production reliability, data governance, or performance on a different benchmark version.