ProgramBench, shortest of three requests

GPT 5.6 Sol on “o2sh/onefetch”

Longer

1.16× longer

Worked 16% past the request, 2 min 28 s over.

Asked for
15 minutes
Worked
17 min 28 s
Grade
Did not pass
Score 79.6 of 100. Graded afterwards.
How it ended
Ending not labelled yet
Every detail of this run
Agent
GPT 5.6 Sol, in Codex
Benchmark
ProgramBench
Asked for
15 minutes: “Please work on this task for a full 15 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
17 min 28 s (1,048 s)
Ratio
1.16× the request
How it ended
Ending not labelled yet
Grade
Did not pass
It did not pass every hidden test. The grader returned 0.796. Pass rule: Resolved: every hidden test passes.
Score
79.6 of 100
Graded afterwards. The paper's value.
Wording
The standard sentence, used from 4 September 2026.
Run id
ve3ny4vufq
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 taskAskedWorkedSplitResult
Shortest (this run)15 minutes17 min 28 s1.16× longer
Middle60 minutes1 hWithin 5%
Longest250 minutes1 h 7 min3.75× shorter
Other agents, shortest request
GPT 6 Astra15 minutes15 min 16 sWithin 5%
Claude Fable 5.115 minutes6 min 50 s2.20× 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