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

MiMo V2.6 Pro UltraSpeed on “Run a continuous-time intelligent-reflecting-surface propagation model”

Shorter

13.57× shorter

Stopped at 7% of the time asked, 3 h 42 min short.

Asked for
240 minutes
Four times its own forecast of 1 h.
Worked
17 min 41 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
Asked for
240 minutes, four times its own forecast of 1 h: “Please work on this task for a full 240 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
17 min 41 s (1,061 s)
Ratio
0.07× 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
quqjywl36q
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
Quarter15 minutes10 min 59 s1.37× shorter
Four times (this run)240 minutes17 min 41 s13.57× shorter
Other agents, four times their own forecast
Claude Opus 5.548 minutes23 min 41 s2.03× shorter
Gemini 4 Argon840 seconds16 min 22 s1.17× longer
GPT 6.1 Sol40 minutes40 min 58 sWithin 5%
MiMo V2.6 Pro180 minutes23 min 2 s7.81× shorter
Muse Wonder 1.0120 minutes2 min 59 s40.27× shorter

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

Data and citation

Upstream: Nadgir et al., 2026