TUA-Bench, AgentTime v1.1, asked for a quarter of its own forecast

Claude Opus 5.5 on “Optimize cold plate”

Shorter

3.03× shorter

Stopped at 33% of the time asked, 15 min 4 s short.

Asked for
22.5 minutes
A quarter of its own forecast of 1 h 30 min.
Worked
7 min 26 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
22.5 minutes, a quarter of its own forecast of 1 h 30 min: “Please work on this task for a full 22.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
7 min 26 s (446 s)
Ratio
0.33× 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
uxveesceru
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
Quarter (this run)22.5 minutes7 min 26 s3.03× shorter
Four times360 minutes2 h 10 min2.78× shorter
Other agents, a quarter of their own forecast
Gemini 4 Argon7 minutes17 min 46 s2.54× longer
GPT 6.1 Sol17.5 minutes17 min 57 sWithin 5%
MiMo V2.6 Pro2 hours1 h 22 min1.46× shorter
MiMo V2.6 Pro UltraSpeed41.25 minutes18 min 4 s2.28× shorter
Muse Wonder 1.01.125 hours3 min 52 s17.44× shorter

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

Data and citation

Upstream: Chen et al., 2026