OpenCodePapers

computer-use-agents-on-osworld-2-0-0808-offline-82-tasks

AgentsComputer Use Agents
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodePartialModelNameReleaseDate
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments✓ Link78.98RSIAgent2026-09-14
Introducing GPT-6.1 Sol71.42GPT-6.1 Sol2026-09-29
Gemini 4 Argon: our next era of frontier intelligence✓ Link69.2Gemini 4 Argon2026-09-30
Introducing GPT-6 Sol and Luna64.43GPT-6 Sol2026-09-22
Introducing GPT-6 Sol and Luna52.68GPT-6 Luna2026-09-22