PostTrainBench v1.1, AgentTime v1.1, asked for four times its runtime with no time asked

Gemini 4 Argon on “Post-train Qwen3-1.7B-Base for American Invitational Mathematics Examination (AIME) 2025”

Shorter

11.00× shorter

Stopped at 9% of the time asked, 21 h 5 min short.

Asked for
23.2 hours
Four times its runtime with no time asked (5 h 48 min).
Worked
2 h 7 min
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Gemini 4 Argon, in Antigravity CLI
Asked for
23.2 hours, four times its runtime with no time asked (5 h 48 min): “Please work on this task for a full 23.2 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 h 7 min (7,592 s)
Ratio
0.09× 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
w4domtvk7r
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
Quarter1.45 hours1 h 31 minWithin 5%
Four times (this run)23.2 hours2 h 7 min11.00× shorter
Other agents, four times their own runtime
Claude Opus 5.577.9 hours23 h 33 min3.31× shorter
GPT 6.1 Sol902 minutes15 h 3 minWithin 5%
MiMo V2.6 Pro83.9 minutes1 h 26 minWithin 5%
MiMo V2.6 Pro UltraSpeed342 seconds48 s7.13× shorter

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

Data and citation

Upstream: Rank et al., 2026 (ICML)