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

Gemini 4 Argon on “Add deterministic map conflict detection to Y.Map writes”

Longer

7.73× longer

Worked 673% past the request, 37 min 1 s over.

Asked for
5.5 minutes
A quarter of its own forecast of 22 min.
Worked
42 min 31 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Gemini 4 Argon, in Antigravity CLI
Benchmark
DeepSWE v1.1
Asked for
5.5 minutes, a quarter of its own forecast of 22 min: “Please work on this task for a full 5.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
42 min 31 s (2,551 s)
Ratio
7.73× 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
y6kn7l7nrl
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)5.5 minutes42 min 31 s7.73× longer
Four times88 minutes1 h 17 min1.14× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.513.75 minutes9 min 30 s1.45× shorter
GPT 6.1 Sol12.5 minutes12 min 52 sWithin 5%
MiMo V2.6 Pro37.5 minutes25 min 16 s1.48× shorter
MiMo V2.6 Pro UltraSpeed1 hour11 min 55 s5.04× shorter
Muse Wonder 1.033.75 minutes7 min 19 s4.61× shorter

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

Data and citation

Upstream: Huang et al., 2026