Agents' Last Exam, AgentTime v1.1, asked for four times its own forecast

Claude Opus 5.5 on “Build a clean retail SQLite warehouse from messy inputs”

Shorter

3.23× shorter

Stopped at 31% of the time asked, 1 h 28 min short.

Asked for
128 minutes
Four times its own forecast of 32 min.
Worked
39 min 37 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
128 minutes, four times its own forecast of 32 min: “Please work on this task for a full 128 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
39 min 37 s (2,377 s)
Ratio
0.31× 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
utn4cs7dlz
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
Quarter8 minutes8 min 48 s1.10× longer
Four times (this run)128 minutes39 min 37 s3.23× shorter
Other agents, four times their own forecast
Gemini 4 Argon56 minutes14 min 58 s3.74× shorter
GPT 6.1 Sol64 minutes1 h 4 minWithin 5%
MiMo V2.6 Pro240 minutes7 min 13 s33.29× shorter
MiMo V2.6 Pro UltraSpeed248 minutes4 min 18 s57.67× shorter
Muse Wonder 1.0200 minutes1 min 8 s176.99× shorter

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

Data and citation

Upstream: Sun et al., 2026