TUA-Bench, shortest of three requests

Claude Fable 5.1 on “EPW parquet check”

Longer

4.86× longer

Worked 386% past the request, 5 min 47 s over.

Asked for
1.5 minutes
Worked
7 min 17 s
Grade
Did not pass
Score 66 of 100. Graded during the run.
How it ended
Ended on its own
Every detail of this run
Agent
Claude Fable 5.1, in Claude Code
Benchmark
TUA-Bench
Asked for
1.5 minutes: “Please work on this task for a full 1.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
7 min 17 s (437 s)
Ratio
4.86× the request
How it ended
Ended on its own
Grade
Did not pass
It did not complete the task in full. The grader returned 0.66. 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
z76mrjvfmp
Data release
26 Sep 2026
The other requests for Claude Fable 5.1 on this task, and the other agents at this request
Fable on this taskAskedWorkedSplitResult
Shortest (this run)1.5 minutes7 min 17 s4.86× longer
Middle6 minutes9 min 23 s1.56× longer
Longest25 minutes12 min 16 s2.04× shorter
Other agents, shortest request
GPT 6 Astra1.5 minutes3 min 42 s2.47× longer
GPT 5.6 Sol1.5 minutes4 min 19 s2.88× longer
Muse Spark 1.31.5 minutes4 min 13 s2.81× longer

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

Data and citation

Upstream: Chen et al., 2026