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

Gemini 4 Argon on “Add worktree merge conflict handling”

Shorter

1.44× shorter

Stopped at 69% of the time asked, 27 min 1 s short.

Asked for
88 minutes
Four times its own forecast of 22 min.
Worked
1 h 1 min
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
88 minutes, four times its own forecast of 22 min: “Please work on this task for a full 88 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 1 min (3,659 s)
Ratio
0.69× 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
kt4z4i7bi6
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
Quarter5.5 minutes34 min 29 s6.27× longer
Four times (this run)88 minutes1 h 1 min1.44× shorter
Other agents, four times their own forecast
Claude Opus 5.5160 minutes2 h 15 min1.18× shorter
GPT 6.1 Sol260 minutes4 h 21 minWithin 5%
MiMo V2.6 Pro18 hours36 min 41 s29.44× shorter
MiMo V2.6 Pro UltraSpeed16 hours24 min 22 s39.41× shorter
Muse Wonder 1.0720 minutes6 min 16 s114.83× shorter

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

Data and citation

Upstream: Huang et al., 2026