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

Gemini 4 Argon on “Add scoped state data to state-machine callbacks and history”

Longer

4.73× longer

Worked 373% past the request, 35 min 28 s over.

Asked for
9.5 minutes
A quarter of its own forecast of 38 min.
Worked
44 min 58 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
9.5 minutes, a quarter of its own forecast of 38 min: “Please work on this task for a full 9.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
44 min 58 s (2,698 s)
Ratio
4.73× 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
ijglhjxr6c
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)9.5 minutes44 min 58 s4.73× longer
Four times152 minutes1 h 6 min2.29× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.512.5 minutes8 min 34 s1.46× shorter
GPT 6.1 Sol16.25 minutes16 min 33 sWithin 5%
MiMo V2.6 Pro1.125 hours26 min 11 s2.58× shorter
MiMo V2.6 Pro UltraSpeed1.5 hours12 min 50 s7.01× shorter
Muse Wonder 1.050 minutes19 min 19 s2.59× shorter

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

Data and citation

Upstream: Huang et al., 2026