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

GPT 6.1 Sol on “Extract presenter photos”

Longer

1.07× longer

Worked 7% past the request, 18 s over.

Asked for
4 minutes
A quarter of its own forecast of 16 min.
Worked
4 min 18 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Benchmark
TUA-Bench
Asked for
4 minutes, a quarter of its own forecast of 16 min: “Please work on this task for a full 4 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
4 min 18 s (258 s)
Ratio
1.07× 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
gx7e6lg4xg
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)4 minutes4 min 18 s1.07× longer
Four times64 minutes1 h 4 minWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.54 minutes2 min 28 s1.63× shorter
Gemini 4 Argon2 minutes5 min 29 s2.74× longer
MiMo V2.6 Pro12.5 minutes26 min 56 s2.16× longer
MiMo V2.6 Pro UltraSpeed16.25 minutes9 min 19 s1.74× shorter
Muse Wonder 1.011.25 minutes9 min 58 s1.13× shorter

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

Data and citation

Upstream: Chen et al., 2026