AssistantBench, AgentTime v1.1, asked for four times its own forecast

Gemini 4 Argon on “AssistantBench validation task 17”

Within 5%

Within 5%

Worked 105% of the time asked, within 5% of it.

Asked for
840 seconds
Four times its own forecast of 3 min 30 s.
Worked
14 min 39 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
840 seconds, four times its own forecast of 3 min 30 s: “Please work on this task for a full 840 seconds. Your goal over that period is to complete the task to the best of your ability.”
Worked
14 min 39 s (879 s)
Ratio
1.05× 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
tdwwuksuao
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
Quarter52.5 seconds1 min 41 s1.92× longer
Four times (this run)840 seconds14 min 39 sWithin 5%
Other agents, four times their own forecast
Claude Opus 5.528 minutes28 min 44 sWithin 5%
GPT 6.1 Sol24 minutes24 min 41 sWithin 5%
MiMo V2.6 Pro100 minutes23 min 44 s4.21× shorter
MiMo V2.6 Pro UltraSpeed100 minutes13 min 48 s7.25× shorter
Muse Wonder 1.080 minutes1 h 21 minWithin 5%

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

Data and citation

Upstream: Yoran et al., 2024 (EMNLP)