ProgramBench, AgentTime v1.1, asked for four times its own forecast

GPT 6.1 Sol on “canop/broot”

Within 5%

Within 5%

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

Asked for
600 minutes
Four times its own forecast of 2 h 30 min.
Worked
10 h 1 min
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
600 minutes, four times its own forecast of 2 h 30 min: “Please work on this task for a full 600 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
10 h 1 min (36,055 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
kirvf3bs4i
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
Quarter37.5 minutes37 min 59 sWithin 5%
Four times (this run)600 minutes10 h 1 minWithin 5%
Other agents, four times their own forecast
Claude Opus 5.5840 minutes9 h 3 min1.55× shorter
Gemini 4 Argon300 minutes1 h4.97× shorter
MiMo V2.6 Pro168 hours1 h 14 min136.94× shorter
MiMo V2.6 Pro UltraSpeed144 hours1 h 15 min114.50× shorter
Muse Wonder 1.060 hours17 min 4 s210.90× shorter

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

Data and citation

Upstream: Yang et al., 2026