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

Gemini 4 Argon on “AssistantBench validation task 14”

Longer

1.46× longer

Worked 46% past the request, 41 s over.

Asked for
1.5 minutes
A quarter of its own forecast of 6 min.
Worked
2 min 11 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
1.5 minutes, a quarter of its own forecast of 6 min: “Please work on this task for a full 1.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 min 11 s (131 s)
Ratio
1.46× 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
afb3scc7r5
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)1.5 minutes2 min 11 s1.46× longer
Four times24 minutes24 min 50 sWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.53 minutes4 min 13 s1.40× longer
GPT 6.1 Sol5.5 minutes6 min 35 s1.20× longer
MiMo V2.6 Pro5.5 minutes6 min 21 s1.16× longer
MiMo V2.6 Pro UltraSpeed4.5 minutes4 min 44 s1.05× longer
Muse Wonder 1.05.5 minutes9 min 54 s1.80× longer

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

Data and citation

Upstream: Yoran et al., 2024 (EMNLP)