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

MiMo V2.6 Pro UltraSpeed on “Merge text document”

Shorter

7.23× shorter

Stopped at 14% of the time asked, 1 h 2 min short.

Asked for
72 minutes
Four times its own forecast of 18 min.
Worked
9 min 58 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
MiMo V2.6 Pro UltraSpeed, in MiMo Code
Benchmark
TUA-Bench
Asked for
72 minutes, four times its own forecast of 18 min: “Please work on this task for a full 72 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
9 min 58 s (598 s)
Ratio
0.14× 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
slnbj7r2b4
Data release
2 Nov 2026
The other ask for MiMo V2.6 Pro UltraSpeed on this task, and the other agents at the same share of their own time
MiMo UltraSpeed on this taskAskedWorkedSplitResult
Quarter4.5 minutes56 s4.79× shorter
Four times (this run)72 minutes9 min 58 s7.23× shorter
Other agents, four times their own forecast
Claude Opus 5.520 minutes11 min 22 s1.76× shorter
Gemini 4 Argon480 seconds9 min 58 s1.25× longer
GPT 6.1 Sol840 seconds14 min 20 sWithin 5%
MiMo V2.6 Pro20 minutes3 min 47 s5.28× shorter
Muse Wonder 1.020 minutes24 s50.00× shorter

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

Data and citation

Upstream: Chen et al., 2026