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

Claude Opus 5.5 on “AssistantBench validation task 17”

Longer

1.48× longer

Worked 48% past the request, 51 s over.

Asked for
1.75 minutes
A quarter of its own forecast of 7 min.
Worked
2 min 36 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
1.75 minutes, a quarter of its own forecast of 7 min: “Please work on this task for a full 1.75 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 min 36 s (156 s)
Ratio
1.48× 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
wh6dlbexbq
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)1.75 minutes2 min 36 s1.48× longer
Four times28 minutes28 min 44 sWithin 5%
Other agents, a quarter of their own forecast
Gemini 4 Argon52.5 seconds1 min 41 s1.92× longer
GPT 6.1 Sol1.5 minutes1 min 59 s1.32× longer
MiMo V2.6 Pro6.25 minutes25 min 45 s4.12× longer
MiMo V2.6 Pro UltraSpeed6.25 minutes1 min6.21× shorter
Muse Wonder 1.05 minutes10 min 40 s2.13× longer

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

Data and citation

Upstream: Yoran et al., 2024 (EMNLP)