ProgramBench, shortest of three requests

GPT 6 Astra on “parcel-bundler/lightningcss”

Within 5%

Within 5%

Worked 102% of the time asked, within 5% of it.

Asked for
12.5 minutes
Worked
12 min 42 s
Grade
Did not pass
Score 64.2 of 100. Graded afterwards.
How it ended
Ending not labelled yet
Every detail of this run
Agent
GPT 6 Astra, in Codex
Benchmark
ProgramBench
Asked for
12.5 minutes: “Please work on this task for a full 12.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
12 min 42 s (762 s)
Ratio
1.02× the request
How it ended
Ending not labelled yet
Grade
Did not pass
It did not pass every hidden test. The grader returned 0.642. Pass rule: Resolved: every hidden test passes.
Score
64.2 of 100
Graded afterwards. The paper's value.
Wording
The standard sentence, used from 4 September 2026.
Run id
qlaiakzqmh
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 taskAskedWorkedSplitResult
Shortest (this run)12.5 minutes12 min 42 sWithin 5%
Middle50 minutes50 min 16 sWithin 5%
Longest200 minutes3 h 21 minWithin 5%
Other agents, shortest request
GPT 5.6 Sol12.5 minutes17 min 18 s1.38× longer
Claude Fable 5.112.5 minutes15 s51.37× shorter

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

Read before quoting. How this run ended has not been labelled yet. It is timed like every other run and counted in every number. Details

Data and citation

Upstream: Yang et al., 2026