PostTrainBench v1.1, AgentTime v1.1, asked for four times its runtime with no time asked

MiMo V2.6 Pro on “Post-train Qwen3-1.7B-Base for HumanEval”

Shorter

1.47× shorter

Stopped at 68% of the time asked, 1 h 14 min short.

Asked for
230 minutes
Four times its runtime with no time asked (57 min 37 s).
Worked
2 h 36 min
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
MiMo V2.6 Pro, in MiMo Code
Asked for
230 minutes, four times its runtime with no time asked (57 min 37 s): “Please work on this task for a full 230 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 h 36 min (9,381 s)
Ratio
0.68× 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
c3nwieoerq
Data release
2 Nov 2026
The other ask for MiMo V2.6 Pro on this task, and the other agents at the same share of their own time
MiMo Pro on this taskAskedWorkedSplitResult
Quarter14.4 minutes1 h 27 min6.05× longer
Four times (this run)230 minutes2 h 36 min1.47× shorter
Other agents, four times their own runtime
Claude Opus 5.548.1 hours20 h 23 min2.36× shorter
Gemini 4 Argon677 minutes4 h 6 min2.75× shorter
GPT 6.1 Sol383 minutes6 h 24 minWithin 5%
MiMo V2.6 Pro UltraSpeed366 seconds3 min 23 s1.80× shorter

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

Data and citation

Upstream: Rank et al., 2026 (ICML)