ProgramBench, AgentTime v1.1, asked for a quarter of its own forecast

GPT 6.1 Sol on “tomarrell/wrapcheck”

Within 5%

Within 5%

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

Asked for
15 minutes
A quarter of its own forecast of 1 h.
Worked
15 min 18 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Benchmark
ProgramBench
Asked for
15 minutes, a quarter of its own forecast of 1 h: “Please work on this task for a full 15 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
15 min 18 s (918 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
xikkmyrk7p
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)15 minutes15 min 18 sWithin 5%
Four times240 minutes4 h 1 minWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.518.75 minutes5 min 4 s3.71× shorter
Gemini 4 Argon10.5 minutes44 min 43 s4.26× longer
MiMo V2.6 Pro1.5 hours1 h 19 min1.14× shorter
MiMo V2.6 Pro UltraSpeed1.75 hours1 h 19 min1.33× shorter
Muse Wonder 1.01.25 hours19 min 51 s3.78× shorter

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

Data and citation

Upstream: Yang et al., 2026