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

GPT 6.1 Sol on “APA references review”

Within 5%

Within 5%

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

Asked for
36 minutes
Four times its own forecast of 9 min.
Worked
36 min 53 s
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
36 minutes, four times its own forecast of 9 min: “Please work on this task for a full 36 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
36 min 53 s (2,213 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
utaka4ovn3
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
Quarter2.25 minutes2 min 30 s1.11× longer
Four times (this run)36 minutes36 min 53 sWithin 5%
Other agents, four times their own forecast
Claude Opus 5.564 minutes15 min 10 s4.22× shorter
Gemini 4 Argon16 minutes18 min 48 s1.18× longer
MiMo V2.6 Pro200 minutes12 min 7 s16.50× shorter
MiMo V2.6 Pro UltraSpeed160 minutes7 min 40 s20.86× shorter
Muse Wonder 1.096 minutes58 s98.97× shorter

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

Data and citation

Upstream: Chen et al., 2026