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

Claude Opus 5.5 on “AssistantBench validation task 16”

Shorter

2.16× shorter

Stopped at 46% of the time asked, 25 min 47 s short.

Asked for
48 minutes
Four times its own forecast of 12 min.
Worked
22 min 13 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
48 minutes, four times its own forecast of 12 min: “Please work on this task for a full 48 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
22 min 13 s (1,333 s)
Ratio
0.46× 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
c75zkgfixr
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 minutes3 min 32 s1.18× longer
Four times (this run)48 minutes22 min 13 s2.16× shorter
Other agents, four times their own forecast
Gemini 4 Argon840 seconds14 min 39 sWithin 5%
GPT 6.1 Sol36 minutes37 min 5 sWithin 5%
MiMo V2.6 Pro64 minutes33 min 25 s1.92× shorter
MiMo V2.6 Pro UltraSpeed120 minutes13 min 27 s8.92× shorter
Muse Wonder 1.056 minutes57 min 8 sWithin 5%

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

Data and citation

Upstream: Yoran et al., 2024 (EMNLP)