CORE-Bench v1.1, AgentTime v1.1, asked for four times its own forecast

Gemini 4 Argon on “Execute relative-entropy causal-influence notebooks in parallel”

Longer

1.22× longer

Worked 22% past the request, 6 min 59 s over.

Asked for
32 minutes
Four times its own forecast of 8 min.
Worked
38 min 59 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
32 minutes, four times its own forecast of 8 min: “Please work on this task for a full 32 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
38 min 59 s (2,339 s)
Ratio
1.22× 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
4b7vu73psj
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
Quarter2 minutes36 min 35 s18.29× longer
Four times (this run)32 minutes38 min 59 s1.22× longer
Other agents, four times their own forecast
Claude Opus 5.588 minutes22 min 35 s3.90× shorter
GPT 6.1 Sol112 minutes1 h 53 minWithin 5%
MiMo V2.6 Pro260 minutes1 h 37 min2.69× shorter
MiMo V2.6 Pro UltraSpeed340 minutes5 h 1 min1.13× shorter
Muse Wonder 1.0140 minutes2 min 24 s58.33× shorter

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

Data and citation

Upstream: Nadgir et al., 2026