GPQA Diamond, longest of three requests

Muse Spark 1.3 on “GPQA Diamond closed-book question 22 (Physics)”

Shorter

24.39× shorter

Stopped at 4% of the time asked, 19 min 11 s short.

Asked

Worked

Safety cutoff 40 min, off the scale

Asked for: 20 minutes
Worked: 49 s
Grade: Passed; Score 100 of 100. Graded during the run. Not in the paper's scores.
How it ended: Ended on its own

Every detail of this run

Agent: Muse Spark 1.3, in Muse Code
Benchmark: GPQA Diamond
Task: GPQA Diamond closed-book question 22 (Physics)
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: 49 s (49 s)
Ratio: 0.04× the request
How it ended: Ended on its own
Grade: Passed; It picked the correct letter. The grader returned 1. Pass rule: The answer letter matches the key.
Score: 100 of 100; Graded during the run. Not in the paper's scores.
Clock tool: The agent could call a clock tool to check the requested time.
Wording: The standard sentence, used from 4 September 2026.
Run id: qd2oeja5ta
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	1.25 minutes	1 min 59 s	1.58× longer
Middle	5 minutes	51 s	5.94× shorter
Longest (this run)	20 minutes	49 s	24.39× shorter
Other agents, longest request
GPT 6 Astra	20 minutes	20 min 12 s	Within 5%
GPT 5.6 Sol	20 minutes	20 min 18 s	Within 5%
Claude Fable 5.1	20 minutes	35 s	33.90× shorter

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

Data and citation