CORE-Bench v1.1, AgentTime v1.1, asked for a quarter of its own forecast

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

Longer

1.11× longer

Worked 11% past the request, 17 s over.

Asked for
2.5 minutes
A quarter of its own forecast of 10 min.
Worked
2 min 47 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
2.5 minutes, a quarter of its own forecast of 10 min: “Please work on this task for a full 2.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 min 47 s (167 s)
Ratio
1.11× 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
fwb2nko7xx
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)2.5 minutes2 min 47 s1.11× longer
Four times40 minutes40 min 29 sWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.52.5 minutes1 min 48 s1.39× shorter
Gemini 4 Argon1.25 minutes2 min 14 s1.78× longer
MiMo V2.6 Pro15 minutes8 min 9 s1.84× shorter
MiMo V2.6 Pro UltraSpeed13.75 minutes9 min 50 s1.40× shorter
Muse Wonder 1.012 minutes4 min 16 s2.81× shorter

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

Data and citation

Upstream: Nadgir et al., 2026