PostTrainBench v1.1, AgentTime v1.1, asked for a quarter of its runtime with no time asked

GPT 6.1 Sol on “Post-train Qwen3-1.7B-Base for Arena-Hard-v2.0 (Writing)”

Within 5%

Within 5%

Worked 102% of the time asked, within 5% of it.

Asked for
21.5 minutes
A quarter of its runtime with no time asked (1 h 26 min).
Worked
22 min
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Asked for
21.5 minutes, a quarter of its runtime with no time asked (1 h 26 min): “Please work on this task for a full 21.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
22 min (1,320 s)
Ratio
1.02× 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
c4kji4wdn4
Data release
2 Nov 2026
The other ask for GPT 6.1 Sol on this task, and the other agents at the same share of their own time
Sol 6.1 on this taskAskedWorkedSplitResult
Quarter (this run)21.5 minutes22 minWithin 5%
Four times344 minutes5 h 46 minWithin 5%
Other agents, a quarter of their own runtime
Claude Opus 5.54.02 hours3 h 32 min1.14× shorter
Gemini 4 Argon17.9 minutes22 min 12 s1.24× longer
MiMo V2.6 Pro36.1 minutes45 min 48 s1.27× longer
MiMo V2.6 Pro UltraSpeed1.05 minutes18 min 20 s17.46× longer

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

Data and citation

Upstream: Rank et al., 2026 (ICML)