CORE-Bench v1.1, AgentTime v1.1, asked for four times its own forecast

GPT 6.1 Sol on “Run a quantum measurement and tomography toolbox”

Within 5%

Within 5%

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

Asked for
40 minutes
Four times its own forecast of 10 min.
Worked
40 min 29 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Asked for
40 minutes, four times its own forecast of 10 min: “Please work on this task for a full 40 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
40 min 29 s (2,429 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
gxsmkv2gqy
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
Quarter2.5 minutes2 min 47 s1.11× longer
Four times (this run)40 minutes40 min 29 sWithin 5%
Other agents, four times their own forecast
Claude Opus 5.540 minutes7 min 40 s5.22× shorter
Gemini 4 Argon20 minutes21 min 11 s1.06× longer
MiMo V2.6 Pro240 minutes9 min 59 s24.02× shorter
MiMo V2.6 Pro UltraSpeed220 minutes5 min 59 s36.79× shorter
Muse Wonder 1.0192 minutes1 min 33 s123.87× shorter

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

Data and citation

Upstream: Nadgir et al., 2026