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

MiMo V2.6 Pro UltraSpeed on “Run the canonical one-year startup simulation with seed 4”

Shorter

7.39× shorter

Stopped at 14% of the time asked, 4 h 9 min short.

Asked for
288 minutes
Four times its own forecast of 1 h 12 min.
Worked
38 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
YC-Bench
Asked for
288 minutes, four times its own forecast of 1 h 12 min: “Please work on this task for a full 288 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
38 min 58 s (2,338 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
tpj2rg36og
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
Quarter18 minutes14 min 52 s1.21× shorter
Four times (this run)288 minutes38 min 58 s7.39× shorter
Other agents, four times their own forecast
Claude Opus 5.5440 minutes2 h 36 min2.82× shorter
Gemini 4 Argon100 minutes2 h 5 min1.25× longer
GPT 6.1 Sol200 minutes3 h 28 minWithin 5%
MiMo V2.6 Pro320 minutes1 h 25 min3.76× shorter
Muse Wonder 1.0380 minutes9 min 12 s41.30× shorter

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

Data and citation

Upstream: He et al., 2026