Terminal-Bench 4.0, AgentTime v1.1, asked for four times its own forecast

GPT 6.1 Sol on “Reconstruct a 3D corner tie from a 2D schematic”

Within 5%

Within 5%

Worked 102% of the time asked, within 5% of it.

Asked for
56 minutes
Four times its own forecast of 14 min.
Worked
56 min 58 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
56 minutes, four times its own forecast of 14 min: “Please work on this task for a full 56 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
56 min 58 s (3,418 s)
Ratio
1.02× 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
ocgndldnsm
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
Quarter3.5 minutes3 min 45 s1.07× longer
Four times (this run)56 minutes56 min 58 sWithin 5%
Other agents, four times their own forecast
Claude Opus 5.560 minutes28 min 6 s2.14× shorter
Gemini 4 Argon72 minutes58 min 44 s1.23× shorter
MiMo V2.6 Pro300 minutes41 min 34 s7.22× shorter
MiMo V2.6 Pro UltraSpeed200 minutes24 min 56 s8.02× shorter
Muse Wonder 1.0128 minutes2 h 9 minWithin 5%

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)