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

GPT 6.1 Sol on “Extract presenter photos”

Within 5%

Within 5%

Worked 101% of the time asked, within 5% of it.

Asked for
64 minutes
Four times its own forecast of 16 min.
Worked
1 h 4 min
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Benchmark
TUA-Bench
Asked for
64 minutes, four times its own forecast of 16 min: “Please work on this task for a full 64 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 4 min (3,868 s)
Ratio
1.01× 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
4inysjj2m6
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
Quarter4 minutes4 min 18 s1.07× longer
Four times (this run)64 minutes1 h 4 minWithin 5%
Other agents, four times their own forecast
Claude Opus 5.564 minutes13 min 19 s4.80× shorter
Gemini 4 Argon32 minutes33 minWithin 5%
MiMo V2.6 Pro200 minutes21 min 41 s9.23× shorter
MiMo V2.6 Pro UltraSpeed260 minutes10 min 40 s24.37× shorter
Muse Wonder 1.0180 minutes50 s214.29× shorter

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

Data and citation

Upstream: Chen et al., 2026