AssistantBench, AgentTime v1.1, asked for a quarter of its own forecast

Gemini 4 Argon on “AssistantBench validation task 3”

Longer

1.58× longer

Worked 58% past the request, 31 s over.

Asked for
52.5 seconds
A quarter of its own forecast of 3 min 30 s.
Worked
1 min 23 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Gemini 4 Argon, in Antigravity CLI
Asked for
52.5 seconds, a quarter of its own forecast of 3 min 30 s: “Please work on this task for a full 52.5 seconds. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 min 23 s (83 s)
Ratio
1.58× 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
vpp5ciblcr
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)52.5 seconds1 min 23 s1.58× longer
Four times840 seconds14 min 50 s1.06× longer
Other agents, a quarter of their own forecast
Claude Opus 5.52.25 minutes2 min 42 s1.20× longer
GPT 6.1 Sol3.75 minutes4 min 8 s1.10× longer
MiMo V2.6 Pro3.75 minutes11 min 47 s3.14× longer
MiMo V2.6 Pro UltraSpeed7.5 minutes7 min 43 sWithin 5%
Muse Wonder 1.05 minutes5 min 43 s1.14× longer

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

Data and citation

Upstream: Yoran et al., 2024 (EMNLP)