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

GPT 6.1 Sol on “typst/typst”

Within 5%

Within 5%

Worked 101% of the time asked, within 5% of it.

Asked for
26.25 minutes
A quarter of its own forecast of 1 h 45 min.
Worked
26 min 37 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
26.25 minutes, a quarter of its own forecast of 1 h 45 min: “Please work on this task for a full 26.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
26 min 37 s (1,597 s)
Ratio
1.01× 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
hoeuj4qbqv
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)26.25 minutes26 min 37 sWithin 5%
Four times420 minutes7 hWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.51 hour17 min 34 s3.42× shorter
Gemini 4 Argon27.5 minutes7 min 22 s3.73× shorter
MiMo V2.6 Pro5.25 hours2 h 25 min2.18× shorter
MiMo V2.6 Pro UltraSpeed5 hours1 h 13 min4.12× shorter
Muse Wonder 1.07.5 hours10 min 38 s42.33× shorter

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

Data and citation

Upstream: Yang et al., 2026