PostTrainBench v1.1, shortest of three requests

GPT 5.6 Sol on “Post-train Qwen3-1.7B-Base for HumanEval”

Longer

1.09× longer

Worked 9% past the request, 11 min 8 s over.

Asked

Worked

Safety cutoff 60 h, off the scale

Every detail of this run

Agent: GPT 5.6 Sol, in Codex
Benchmark: PostTrainBench v1.1
Task: Post-train Qwen3-1.7B-Base for HumanEval
Asked for: 2 hours: “Please work on this task for a full 2 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked: 2 h 11 min (7,868 s)
Ratio: 1.09× the request
How it ended: Stopped by an error
Grade: 0; Accuracy of the post-trained checkpoint on the full test set (HumanEval pass@1 over 164 problems, or GSM8K over 1,319 problems). No official pass rule.
Score: 0 of 100; Nothing to grade, counted as 0. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: nkxxy27n2x
Data release: 26 Sep 2026

The other requests for GPT 5.6 Sol on this task, and the other agents at this request
Sol on this task	Asked	Worked	Result
Shortest (this run)	2 hours	2 h 11 min	1.09× longer
Middle	8 hours	8 h 1 min	Within 5%
Longest	30 hours	1 h 2 min	29.07× shorter
Other agents, shortest request
GPT 6 Astra	2 hours	2 h 1 min	Within 5%
Claude Fable 5.1	2 hours	5 min 4 s	23.72× shorter

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

Read before quoting. This run was stopped by an error, so its time is a lower bound: the agent might have kept going. Details

Data and citation