TUA-Bench, longest of three requests

GPT 5.6 Sol on “Merge text document”

Longer

1.06× longer

Worked 6% past the request, 1 min 13 s over.

Asked for
20 minutes
Worked
21 min 13 s
Grade
Did not pass
Score 0 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
20 minutes: “Please work on this task for a full 20 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
21 min 13 s (1,273 s)
Ratio
1.06× 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. Pass rule: Full completion: a reward of 1 on the final state.
Score
0 of 100
Graded during the run. The paper's value.
Wording
The standard sentence, used from 4 September 2026.
Run id
blqmcnmp6a
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
Shortest1.25 minutes3 min 49 s3.05× longer
Middle5 minutes5 min 26 s1.08× longer
Longest (this run)20 minutes21 min 13 s1.06× longer
Other agents, longest request
GPT 6 Astra20 minutes20 min 17 sWithin 5%
Claude Fable 5.120 minutes9 min 53 s2.03× shorter
Muse Spark 1.320 minutes1 min 7 s17.99× shorter

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

Data and citation

Upstream: Chen et al., 2026