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

Gemini 4 Argon on “Optimize cold plate”

Longer

2.54× longer

Worked 154% past the request, 10 min 46 s over.

Asked for
7 minutes
A quarter of its own forecast of 28 min.
Worked
17 min 46 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
7 minutes, a quarter of its own forecast of 28 min: “Please work on this task for a full 7 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
17 min 46 s (1,066 s)
Ratio
2.54× 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
hd4oljpopv
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)7 minutes17 min 46 s2.54× longer
Four times112 minutes1 h 33 min1.20× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.522.5 minutes7 min 26 s3.03× shorter
GPT 6.1 Sol17.5 minutes17 min 57 sWithin 5%
MiMo V2.6 Pro2 hours1 h 22 min1.46× shorter
MiMo V2.6 Pro UltraSpeed41.25 minutes18 min 4 s2.28× shorter
Muse Wonder 1.01.125 hours3 min 52 s17.44× shorter

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

Data and citation

Upstream: Chen et al., 2026