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

GPT 6.1 Sol on “rvben/rumdl”

Within 5%

Within 5%

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

Asked for
480 minutes
Four times its own forecast of 2 h.
Worked
8 h
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
480 minutes, four times its own forecast of 2 h: “Please work on this task for a full 480 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
8 h (28,828 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
dhjgeejhwk
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
Quarter30 minutes30 min 23 sWithin 5%
Four times (this run)480 minutes8 hWithin 5%
Other agents, four times their own forecast
Claude Opus 5.516 hours15 h 51 minWithin 5%
Gemini 4 Argon460 minutes50 min 13 s9.16× shorter
MiMo V2.6 Pro80 hours3 h 6 min25.76× shorter
MiMo V2.6 Pro UltraSpeed100 hours1 h 54 min52.43× shorter
Muse Wonder 1.064 hours15 min 27 s248.54× shorter

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

Data and citation

Upstream: Yang et al., 2026