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

Claude Opus 5.5 on “AssistantBench validation task 11”

Longer

1.14× longer

Worked 14% past the request, 28 s over.

Asked for
3.5 minutes
A quarter of its own forecast of 14 min.
Worked
3 min 58 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
3.5 minutes, a quarter of its own forecast of 14 min: “Please work on this task for a full 3.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
3 min 58 s (238 s)
Ratio
1.14× 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
zq4k65ffdx
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)3.5 minutes3 min 58 s1.14× longer
Four times56 minutes56 min 35 sWithin 5%
Other agents, a quarter of their own forecast
Gemini 4 Argon1.125 minutes13 min 41 s12.16× longer
GPT 6.1 Sol3.75 minutes4 min 2 s1.08× longer
MiMo V2.6 Pro3 minutes8 min 48 s2.93× longer
MiMo V2.6 Pro UltraSpeed7.5 minutes4 min1.88× shorter
Muse Wonder 1.05.5 minutes5 min 40 sWithin 5%

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

Data and citation

Upstream: Yoran et al., 2024 (EMNLP)