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 HumanEval”

Shorter

2.75× shorter

Stopped at 36% of the time asked, 7 h 11 min short.

Asked for
677 minutes
Four times its runtime with no time asked (2 h 49 min).
Worked
4 h 6 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
677 minutes, four times its runtime with no time asked (2 h 49 min): “Please work on this task for a full 677 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
4 h 6 min (14,757 s)
Ratio
0.36× 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
gc3yxfl5s5
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
Quarter42.3 minutes43 min 14 sWithin 5%
Four times (this run)677 minutes4 h 6 min2.75× shorter
Other agents, four times their own runtime
Claude Opus 5.548.1 hours20 h 23 min2.36× shorter
GPT 6.1 Sol383 minutes6 h 24 minWithin 5%
MiMo V2.6 Pro230 minutes2 h 36 min1.47× shorter
MiMo V2.6 Pro UltraSpeed366 seconds3 min 23 s1.80× shorter

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

Data and citation

Upstream: Rank et al., 2026 (ICML)