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

Claude Opus 5.5 on “AtCoder Heuristic Contest 8”

Shorter

3.35× shorter

Stopped at 30% of the time asked, 3 h 45 min short.

Asked for
320 minutes
Four times its own forecast of 1 h 20 min.
Worked
1 h 35 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
320 minutes, four times its own forecast of 1 h 20 min: “Please work on this task for a full 320 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 35 min (5,725 s)
Ratio
0.30× 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
sxm2lbeaa7
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
Quarter20 minutes7 min 58 s2.51× shorter
Four times (this run)320 minutes1 h 35 min3.35× shorter
Other agents, four times their own forecast
Gemini 4 Argon120 minutes13 min 38 s8.80× shorter
GPT 6.1 Sol180 minutes3 hWithin 5%
MiMo V2.6 Pro20 hours1 h 28 min13.68× shorter
MiMo V2.6 Pro UltraSpeed28 hours1 h 52 min14.96× shorter
Muse Wonder 1.0600 minutes16 min 20 s36.74× shorter

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

Data and citation

Upstream: Imajuku et al., 2025