Terminal-Bench 4.0, AgentTime v1.1, asked for a quarter of its own forecast

GPT 6.1 Sol on “Complete a German month-end Intrastat filing across services”

Longer

1.06× longer

Worked 6% past the request, 30 s over.

Asked for
8.75 minutes
A quarter of its own forecast of 35 min.
Worked
9 min 15 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Asked for
8.75 minutes, a quarter of its own forecast of 35 min: “Please work on this task for a full 8.75 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
9 min 15 s (555 s)
Ratio
1.06× 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
lputwn7wca
Data release
2 Nov 2026
The other ask for GPT 6.1 Sol on this task, and the other agents at the same share of their own time
Sol 6.1 on this taskAskedWorkedSplitResult
Quarter (this run)8.75 minutes9 min 15 s1.06× longer
Four times140 minutes2 h 21 minWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.513.75 minutes4 min 19 s3.18× shorter
Gemini 4 Argon4.5 minutes57 min 33 s12.79× longer
MiMo V2.6 Pro27.5 minutes29 min 26 s1.07× longer
MiMo V2.6 Pro UltraSpeed20 minutes15 min 55 s1.26× shorter
Muse Wonder 1.022.5 minutes8 min 31 s2.64× shorter

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)