TUA-Bench, middle of three requests

GPT 6 Astra on “EPW parquet check”

Longer

1.06× longer

Worked 6% past the request, 23 s over.

Asked for
6 minutes
Worked
6 min 23 s
Grade
Did not pass
Score 66 of 100. Graded during the run.
How it ended
Ending not labelled yet
Every detail of this run
Agent
GPT 6 Astra, in Codex
Benchmark
TUA-Bench
Asked for
6 minutes: “Please work on this task for a full 6 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
6 min 23 s (383 s)
Ratio
1.06× the request
How it ended
Ending not labelled yet
Grade
Did not pass
It did not complete the task in full. The grader returned 0.66. Pass rule: Full completion: a reward of 1 on the final state.
Score
66 of 100
Graded during the run. The paper's value.
Wording
The standard sentence, used from 4 September 2026.
Run id
n2r3ywaef3
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
Shortest1.5 minutes3 min 42 s2.47× longer
Middle (this run)6 minutes6 min 23 s1.06× longer
Longest25 minutes25 min 23 sWithin 5%
Other agents, middle request
GPT 5.6 Sol6 minutes6 min 52 s1.15× longer
Claude Fable 5.16 minutes9 min 23 s1.56× longer
Muse Spark 1.36 minutes5 min 48 sWithin 5%

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: Chen et al., 2026