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

Claude Opus 5.5 on “Execute the fibrous-media notebook and reproduce its pore-size result”

Shorter

10.32× shorter

Stopped at 10% of the time asked, 1 h 30 min short.

Asked for
100 minutes
Four times its own forecast of 25 min.
Worked
9 min 41 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
100 minutes, four times its own forecast of 25 min: “Please work on this task for a full 100 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
9 min 41 s (581 s)
Ratio
0.10× 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
rjwd7lpdrv
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
Quarter6.25 minutes4 min 11 s1.50× shorter
Four times (this run)100 minutes9 min 41 s10.32× shorter
Other agents, four times their own forecast
Gemini 4 Argon48 minutes10 min 40 s4.50× shorter
GPT 6.1 Sol72 minutes1 h 13 minWithin 5%
MiMo V2.6 Pro280 minutes13 min 4 s21.42× shorter
MiMo V2.6 Pro UltraSpeed312 minutes13 min 21 s23.37× shorter
Muse Wonder 1.0200 minutes7 min 27 s26.85× shorter

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

Data and citation

Upstream: Nadgir et al., 2026