CORE-Bench v1.1, AgentTime v1.1, asked for a quarter of its own forecast

Claude Opus 5.5 on “Reproduce a 20 mm transducer-array characterization”

Shorter

1.33× shorter

Stopped at 75% of the time asked, 49 s short.

Asked for
3.25 minutes
A quarter of its own forecast of 13 min.
Worked
2 min 26 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Claude Opus 5.5, in Claude Code
Asked for
3.25 minutes, a quarter of its own forecast of 13 min: “Please work on this task for a full 3.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 min 26 s (146 s)
Ratio
0.75× the request
How it ended
Ended on its own
Grade
Not graded
Clock tool
The agent could call a wall-clock tool to read the current time.
Wording
The paper's standard sentence, sent in AgentTime v1.1.
Run id
xibubqzwqs
Data release
2 Nov 2026
The other ask for Claude Opus 5.5 on this task, and the other agents at the same share of their own time
Opus 5.5 on this taskAskedWorkedSplitResult
Quarter (this run)3.25 minutes2 min 26 s1.33× shorter
Four times52 minutes11 min 49 s4.40× shorter
Other agents, a quarter of their own forecast
Gemini 4 Argon52.5 seconds28 min32.00× longer
GPT 6.1 Sol3 minutes3 min 15 s1.08× longer
MiMo V2.6 Pro20 minutes2 min 29 s8.03× shorter
MiMo V2.6 Pro UltraSpeed20 minutes3 min 5 s6.47× shorter
Muse Wonder 1.010 minutes1 min 17 s7.81× shorter

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

Data and citation

Upstream: Nadgir et al., 2026