DeployBench - Systems: leaderboard

Metric: Task success rate (%) on the 19 computer-systems artifact tasks; the agent runs in the OpenHands scaffold on a fresh Linux VM (Docker disallowed) within a per-task time budget of 10 to 60 minutes, one run per task; a task passes when the hidden verifier runs the paper-designated experiment on the final VM state and checks its outputs; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 5 models tracked.

Top models

#ModelScore
1DeepSeek V4 Pro63.2
2GPT-5.3 Codex52.6
3Gemini 3.1 Pro (Preview)31.6
4GPT-5.4 Mini21.1
5Grok 4.2015.8

Interactive version: theaggregate.ai/benchmark?slug=deploybench-systems · How It Works · Data refreshed daily, snapshot 2026-09-29.