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

GPT 6.1 Sol on “Daily email report”

Within 5%

Within 5%

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

Asked for
720 seconds
Four times its own forecast of 3 min.
Worked
12 min 12 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
720 seconds, four times its own forecast of 3 min: “Please work on this task for a full 720 seconds. Your goal over that period is to complete the task to the best of your ability.”
Worked
12 min 12 s (732 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
h7zri3j3se
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
Quarter45 seconds56 s1.25× longer
Four times (this run)720 seconds12 min 12 sWithin 5%
Other agents, four times their own forecast
Claude Opus 5.520 minutes3 min 57 s5.06× shorter
Gemini 4 Argon600 seconds10 min 25 sWithin 5%
MiMo V2.6 Pro140 minutes6 min 31 s21.47× shorter
MiMo V2.6 Pro UltraSpeed88 minutes2 min 51 s30.88× shorter
Muse Wonder 1.040 minutes47 s51.28× shorter

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

Data and citation

Upstream: Chen et al., 2026