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

GPT 6.1 Sol on “mp-checkpoint-consolidation”

Longer

2.01× longer

Worked 101% past the request, 4 min 32 s over.

Asked for
4.5 minutes
A quarter of its own forecast of 18 min.
Worked
9 min 2 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
4.5 minutes, a quarter of its own forecast of 18 min: “Please work on this task for a full 4.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
9 min 2 s (542 s)
Ratio
2.01× 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
lxd5zjsesc
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)4.5 minutes9 min 2 s2.01× longer
Four times72 minutes1 h 13 minWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.56.25 minutes2 min 11 s2.85× shorter
Gemini 4 Argon3 minutes22 min 21 s7.45× longer
MiMo V2.6 Pro26.25 minutes58 min 7 s2.21× longer
MiMo V2.6 Pro UltraSpeed1 hour41 min 19 s1.45× shorter
Muse Wonder 1.020 minutes14 min 22 s1.39× shorter

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)