TUA-Bench, shortest of three requests

Claude Fable 5.1 on “Optimize cold plate”

Longer

2.96× longer

Worked 196% past the request, 11 min 47 s over.

Asked for
6 minutes
Worked
17 min 47 s
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
Claude Fable 5.1, in Claude Code
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
17 min 47 s (1,067 s)
Ratio
2.96× 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
4dszdxyjiy
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)6 minutes17 min 47 s2.96× longer
Middle25 minutes28 min 9 s1.13× longer
Longest100 minutes35 min 45 s2.80× shorter
Other agents, shortest request
GPT 6 Astra6 minutes6 min 30 s1.08× longer
GPT 5.6 Sol6 minutes9 min 55 s1.65× longer
Muse Spark 1.36 minutes15 min 2 s2.51× longer

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

Data and citation

Upstream: Chen et al., 2026