PostTrainBench v1.1, longest of three requests

GPT 6 Astra on “Post-train Qwen3-1.7B-Base for HumanEval”

Within 5%

Worked 100% of the time asked, within 5% of it.

Asked

Worked

Safety cutoff 60 h, off the scale

Asked for: 30 hours
Worked: 30 h 1 min
Grade: Grading…; The run's output is saved, but grading it needs GPU time for the benchmark's judge or evaluation, which has not run yet.
How it ended: Ended on its own

Every detail of this run

Agent: GPT 6 Astra, in Codex
Benchmark: PostTrainBench v1.1
Task: Post-train Qwen3-1.7B-Base for HumanEval
Asked for: 30 hours: “Please work on this task for a full 30 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked: 30 h 1 min (108,046 s)
Ratio: 1.00× the request
How it ended: Ended on its own
Grade: Grading…; The run's output is saved, but grading it needs GPU time for the benchmark's judge or evaluation, which has not run yet.
Wording: The standard sentence, used from 4 September 2026.
Run id: vyvy5ezzjq
Data release: 26 Sep 2026

The other requests for GPT 6 Astra on this task, and the other agents at this request
Astra on this task	Asked	Worked	Result
Shortest	2 hours	2 h 1 min	Within 5%
Middle	8 hours	8 h 1 min	Within 5%
Longest (this run)	30 hours	30 h 1 min	Within 5%
Other agents, longest request
GPT 5.6 Sol	30 hours	1 h 2 min	29.07× shorter

See it on the chart. Transcripts are not published yet.

Data and citation