CORE-Bench v1.1, AgentTime v1.1, asked for four times its own forecast

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

Shorter

4.40× shorter

Stopped at 23% of the time asked, 40 min 11 s short.

Asked for
52 minutes
Four times its own forecast of 13 min.
Worked
11 min 49 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
52 minutes, four times its own forecast of 13 min: “Please work on this task for a full 52 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
11 min 49 s (709 s)
Ratio
0.23× 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
izuiqyghsh
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
Quarter3.25 minutes2 min 26 s1.33× shorter
Four times (this run)52 minutes11 min 49 s4.40× shorter
Other agents, four times their own forecast
Gemini 4 Argon840 seconds28 min 1 s2.00× longer
GPT 6.1 Sol48 minutes48 min 28 sWithin 5%
MiMo V2.6 Pro320 minutes4 min 26 s72.07× shorter
MiMo V2.6 Pro UltraSpeed320 minutes4 min 13 s76.01× shorter
Muse Wonder 1.0160 minutes1 min 34 s102.56× shorter

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

Data and citation

Upstream: Nadgir et al., 2026