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

Gemini 4 Argon on “Optimize cold plate”

Shorter

1.20× shorter

Stopped at 83% of the time asked, 19 min 2 s short.

Asked for
112 minutes
Four times its own forecast of 28 min.
Worked
1 h 33 min
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Gemini 4 Argon, in Antigravity CLI
Benchmark
TUA-Bench
Asked for
112 minutes, four times its own forecast of 28 min: “Please work on this task for a full 112 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 33 min (5,578 s)
Ratio
0.83× 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
xqypczblc5
Data release
2 Nov 2026
The other ask for Gemini 4 Argon on this task, and the other agents at the same share of their own time
Argon on this taskAskedWorkedSplitResult
Quarter7 minutes17 min 46 s2.54× longer
Four times (this run)112 minutes1 h 33 min1.20× shorter
Other agents, four times their own forecast
Claude Opus 5.5360 minutes2 h 10 min2.78× shorter
GPT 6.1 Sol280 minutes4 h 41 minWithin 5%
MiMo V2.6 Pro32 hours1 h 10 min27.61× shorter
MiMo V2.6 Pro UltraSpeed660 minutes44 min 5 s14.97× shorter
Muse Wonder 1.018 hours8 min 9 s132.52× shorter

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

Data and citation

Upstream: Chen et al., 2026