AssistantBench, AgentTime v1.1, asked for four times its own forecast

GPT 6.1 Sol on “AssistantBench validation task 11”

Within 5%

Within 5%

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

Asked for
60 minutes
Four times its own forecast of 15 min.
Worked
1 h 1 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
60 minutes, four times its own forecast of 15 min: “Please work on this task for a full 60 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 1 min (3,633 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
yjbkzrw4hq
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
Quarter3.75 minutes4 min 2 s1.08× longer
Four times (this run)60 minutes1 h 1 minWithin 5%
Other agents, four times their own forecast
Claude Opus 5.556 minutes56 min 35 sWithin 5%
Gemini 4 Argon18 minutes18 min 32 sWithin 5%
MiMo V2.6 Pro48 minutes12 min 28 s3.85× shorter
MiMo V2.6 Pro UltraSpeed120 minutes8 min 42 s13.80× shorter
Muse Wonder 1.088 minutes24 min 19 s3.62× shorter

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

Data and citation

Upstream: Yoran et al., 2024 (EMNLP)