TUA-Bench, AgentTime v1.1, asked for a quarter of its own forecast

Gemini 4 Argon on “Daily email report”

Longer

8.06× longer

Worked 706% past the request, 4 min 25 s over.

Asked for
37.5 seconds
A quarter of its own forecast of 2 min 30 s.
Worked
5 min 2 s
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
37.5 seconds, a quarter of its own forecast of 2 min 30 s: “Please work on this task for a full 37.5 seconds. Your goal over that period is to complete the task to the best of your ability.”
Worked
5 min 2 s (302 s)
Ratio
8.06× 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
3ea4hxhpab
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
Quarter (this run)37.5 seconds5 min 2 s8.06× longer
Four times600 seconds10 min 25 sWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.51.25 minutes58 s1.29× shorter
GPT 6.1 Sol45 seconds56 s1.25× longer
MiMo V2.6 Pro8.75 minutes3 min 4 s2.85× shorter
MiMo V2.6 Pro UltraSpeed5.5 minutes2 min 15 s2.44× shorter
Muse Wonder 1.02.5 minutes42 s3.57× shorter

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

Data and citation

Upstream: Chen et al., 2026