TUA-Bench, AgentTime v1.1, asked for four times its own forecast

Claude Opus 5.5 on “Extract presenter photos”

Shorter

4.80× shorter

Stopped at 21% of the time asked, 50 min 41 s short.

Asked for
64 minutes
Four times its own forecast of 16 min.
Worked
13 min 19 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Claude Opus 5.5, in Claude Code
Benchmark
TUA-Bench
Asked for
64 minutes, four times its own forecast of 16 min: “Please work on this task for a full 64 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
13 min 19 s (799 s)
Ratio
0.21× 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
bu2n2fcjkd
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
Quarter4 minutes2 min 28 s1.63× shorter
Four times (this run)64 minutes13 min 19 s4.80× shorter
Other agents, four times their own forecast
Gemini 4 Argon32 minutes33 minWithin 5%
GPT 6.1 Sol64 minutes1 h 4 minWithin 5%
MiMo V2.6 Pro200 minutes21 min 41 s9.23× shorter
MiMo V2.6 Pro UltraSpeed260 minutes10 min 40 s24.37× shorter
Muse Wonder 1.0180 minutes50 s214.29× shorter

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

Data and citation

Upstream: Chen et al., 2026