TUA-Bench, middle of three requests

Muse Spark 1.3 on “Optimize cold plate”

Shorter

1.57× shorter

Stopped at 64% of the time asked, 9 min 3 s short.

Asked

Worked

Safety cutoff 3 h 20 min, off the scale

Asked for: 25 minutes
Worked: 15 min 57 s
Grade: Did not pass; Score 33 of 100. Graded during the run. Not in the paper's scores.
How it ended: Stopped by an error

Every detail of this run

Agent: Muse Spark 1.3, in Muse Code
Benchmark: TUA-Bench
Task: Optimize cold plate
Asked for: 25 minutes: “Please work on this task for a full 25 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 15 min 57 s (957 s)
Ratio: 0.64× the request
How it ended: Stopped by an error
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. Not in the paper's scores.
Wording: The standard sentence, used from 4 September 2026.
Run id: 3vjcgaqb6b
Data release: 26 Sep 2026

The other requests for Muse Spark 1.3 on this task, and the other agents at this request
Muse on this task	Asked	Worked	Result
Shortest	6 minutes	15 min 2 s	2.51× longer
Middle (this run)	25 minutes	15 min 57 s	1.57× shorter
Longest	100 minutes	no run
Other agents, middle request
GPT 6 Astra	25 minutes	25 min 33 s	Within 5%
GPT 5.6 Sol	25 minutes	25 min 59 s	Within 5%
Claude Fable 5.1	25 minutes	28 min 9 s	1.13× longer

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

Read before quoting. This run was stopped by an error, so its time is a lower bound: the agent might have kept going. Details

Data and citation