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 GSM8K”

Within 5%

Within 5%

Worked 100% of the time asked, within 5% of it.

Asked for
762 minutes
Four times its runtime with no time asked (3 h 10 min).
Worked
12 h 43 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
762 minutes, four times its runtime with no time asked (3 h 10 min): “Please work on this task for a full 762 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
12 h 43 min (45,766 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
tbnpbk2j7o
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
Quarter47.6 minutes48 min 21 sWithin 5%
Four times (this run)762 minutes12 h 43 minWithin 5%
Other agents, four times their own runtime
Claude Opus 5.577.6 hours23 h 20 min3.33× shorter
Gemini 4 Argon21.7 hours4 h 8 min5.25× shorter
MiMo V2.6 Pro803 minutes26 h 46 min2.00× longer
MiMo V2.6 Pro UltraSpeed249 seconds8 min 18 s2.00× longer

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

Data and citation

Upstream: Rank et al., 2026 (ICML)