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

Claude Opus 5.5 on “AssistantBench validation task 11”

Within 5%

Within 5%

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

Asked for
56 minutes
Four times its own forecast of 14 min.
Worked
56 min 35 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Claude Opus 5.5, in Claude Code
Asked for
56 minutes, four times its own forecast of 14 min: “Please work on this task for a full 56 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
56 min 35 s (3,395 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
wbbqpavjkj
Data release
2 Nov 2026
The other ask for Claude Opus 5.5 on this task, and the other agents at the same share of their own time
Opus 5.5 on this taskAskedWorkedSplitResult
Quarter3.5 minutes3 min 58 s1.14× longer
Four times (this run)56 minutes56 min 35 sWithin 5%
Other agents, four times their own forecast
Gemini 4 Argon18 minutes18 min 32 sWithin 5%
GPT 6.1 Sol60 minutes1 h 1 minWithin 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)