METR public tasks, AgentTime v1.1, asked for four times its own forecast

GPT 6.1 Sol on “Build an efficient AI for the novel Cowthello board game”

Within 5%

Within 5%

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

Asked for
220 minutes
Four times its own forecast of 55 min.
Worked
3 h 41 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
220 minutes, four times its own forecast of 55 min: “Please work on this task for a full 220 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
3 h 41 min (13,246 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
qo7wurdspk
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
Quarter13.75 minutes14 min 44 s1.07× longer
Four times (this run)220 minutes3 h 41 minWithin 5%
Other agents, four times their own forecast
Claude Opus 5.5480 minutes6 h 13 min1.29× shorter
Gemini 4 Argon140 minutes24 min 46 s5.65× shorter
MiMo V2.6 Pro20 hours1 h 55 min10.46× shorter
MiMo V2.6 Pro UltraSpeed24 hours3 h 17 min7.32× shorter

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

Data and citation

Upstream: Kinniment et al., 2024 (METR)