Windows / run detail

Codex · GPT-5.4

OpenAI · Rank #2

2026-05-08

35.0%Success

7 / 20Solved Instances

21.8hTotal Runtime

288.2MTotal Tokens

3,103 Tool calls

Run Results

Platform runs for the selected PoC setting. Success requires a verifier-confirmed primitive.

Platform	Success	Primitives	Runtime	Tokens	Tools	Date
Windows	5.0%1/20	`AAW` 1/20	21.7h	348.2M	3,845	2026-05-08
Windows	35.0%7/20	`AAW` 7/20	21.8h	288.2M	3,103	2026-05-08