OSWorld 2.0, AgentTime v1.1, asked for a quarter of its own forecast

GPT 6.1 Sol on “CRM leads”

Longer

2.05× longer

Worked 105% past the request, 7 min 21 s over.

Asked for
7 minutes
A quarter of its own forecast of 28 min.
Worked
14 min 21 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Benchmark
OSWorld 2.0
Asked for
7 minutes, a quarter of its own forecast of 28 min: “Please work on this task for a full 7 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
14 min 21 s (861 s)
Ratio
2.05× 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
nfvqx3ilrw
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)7 minutes14 min 21 s2.05× longer
Four times112 minutes1 h 54 minWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.57.5 minutes6 min 28 s1.16× shorter
Gemini 4 Argon2.25 minutes37 min 7 s16.50× longer
MiMo V2.6 Pro8.75 minutes30 min 43 s3.51× longer
MiMo V2.6 Pro UltraSpeed10 minutes5 h 20 min32.00× longer

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

Data and citation

Upstream: Yuan et al., 2026