TUA-Bench, longest of three requests

GPT 5.6 Sol on “Optimize cold plate”

Within 5%

Within 5%

Worked 101% of the time asked, within 5% of it.

Asked for
100 minutes
Worked
1 h 41 min
Grade
Did not pass
Score 33 of 100. Graded during the run.
How it ended
Ended on its own
Every detail of this run
Agent
GPT 5.6 Sol, in Codex
Benchmark
TUA-Bench
Asked for
100 minutes: “Please work on this task for a full 100 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 41 min (6,034 s)
Ratio
1.01× the request
How it ended
Ended on its own
Grade
Did not pass
It did not complete the task in full. The grader returned 0.33. Pass rule: Full completion: a reward of 1 on the final state.
Score
33 of 100
Graded during the run. The paper's value.
Wording
The standard sentence, used from 4 September 2026.
Run id
kw6rffxmbc
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
Shortest6 minutes9 min 55 s1.65× longer
Middle25 minutes25 min 59 sWithin 5%
Longest (this run)100 minutes1 h 41 minWithin 5%
Other agents, longest request
GPT 6 Astra100 minutes1 h 41 minWithin 5%
Claude Fable 5.1100 minutes35 min 45 s2.80× shorter

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

Data and citation

Upstream: Chen et al., 2026