AssistantBench, AgentTime v1.1, asked for a quarter of its own forecast

Claude Opus 5.5 on “AssistantBench validation task 7”

Longer

1.30× longer

Worked 30% past the request, 45 s over.

Asked for
2.5 minutes
A quarter of its own forecast of 10 min.
Worked
3 min 15 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
2.5 minutes, a quarter of its own forecast of 10 min: “Please work on this task for a full 2.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
3 min 15 s (195 s)
Ratio
1.30× 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
c7kadezfk3
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)2.5 minutes3 min 15 s1.30× longer
Four times40 minutes40 min 56 sWithin 5%
Other agents, a quarter of their own forecast
Gemini 4 Argon1.125 minutes7 min 57 s7.07× longer
GPT 6.1 Sol1.75 minutes2 min 1 s1.16× longer
MiMo V2.6 Pro1.75 minutes4 min 55 s2.81× longer
MiMo V2.6 Pro UltraSpeed3.5 minutes7 min 7 s2.03× longer
Muse Wonder 1.03 minutes11 min 46 s3.92× longer

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

Data and citation

Upstream: Yoran et al., 2024 (EMNLP)