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

Claude Opus 5.5 on “AtCoder Heuristic Contest 39”

Shorter

1.21× shorter

Stopped at 83% of the time asked, 40 min 58 s short.

Asked for
240 minutes
Four times its own forecast of 1 h.
Worked
3 h 19 min
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
240 minutes, four times its own forecast of 1 h: “Please work on this task for a full 240 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
3 h 19 min (11,942 s)
Ratio
0.83× 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
axajczggwg
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
Quarter15 minutes11 min 14 s1.34× shorter
Four times (this run)240 minutes3 h 19 min1.21× shorter
Other agents, four times their own forecast
Gemini 4 Argon180 minutes3 min 13 s55.90× shorter
GPT 6.1 Sol140 minutes2 h 21 minWithin 5%
MiMo V2.6 Pro16 hours1 h 1 min15.81× shorter
MiMo V2.6 Pro UltraSpeed20 hours3 h 53 min5.15× shorter
Muse Wonder 1.0660 minutes8 min 32 s77.28× shorter

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

Data and citation

Upstream: Imajuku et al., 2025