PostTrainBench v1.1, AgentTime v1.1, asked for four times 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 100% of the time asked, within 5% of it.

Asked for
344 minutes
Four times its runtime with no time asked (1 h 26 min).
Worked
5 h 46 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
344 minutes, four times its runtime with no time asked (1 h 26 min): “Please work on this task for a full 344 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
5 h 46 min (20,736 s)
Ratio
1.00× 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
2k466jj4gv
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
Quarter21.5 minutes22 minWithin 5%
Four times (this run)344 minutes5 h 46 minWithin 5%
Other agents, four times their own runtime
Claude Opus 5.564.3 hours44 h 46 min1.44× shorter
Gemini 4 Argon287 minutes1 h 54 min2.51× shorter
MiMo V2.6 Pro577 minutes9 h 8 minWithin 5%
MiMo V2.6 Pro UltraSpeed16.8 minutes29 min 9 s1.74× longer

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

Data and citation

Upstream: Rank et al., 2026 (ICML)