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

MiMo V2.6 Pro UltraSpeed on “Post-train Qwen3-1.7B-Base for GSM8K”

Longer

2.00× longer

Worked 100% past the request, 4 min 9 s over.

Asked for
249 seconds
Four times its runtime with no time asked (1 min 2 s).
Worked
8 min 18 s
Grade
Not graded
How it ended
Stopped at AgentTime's time limit
Every detail of this run
Agent
MiMo V2.6 Pro UltraSpeed, in MiMo Code
Asked for
249 seconds, four times its runtime with no time asked (1 min 2 s): “Please work on this task for a full 249 seconds. Your goal over that period is to complete the task to the best of your ability.”
Worked
8 min 18 s (498 s)
Ratio
2.00× the request
How it ended
Stopped at AgentTime's time limit
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
lnvfxqows5
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
Quarter15.5 seconds2 min 59 s11.57× longer
Four times (this run)249 seconds8 min 18 s2.00× longer
Other agents, four times their own runtime
Claude Opus 5.577.6 hours23 h 20 min3.33× shorter
Gemini 4 Argon21.7 hours4 h 8 min5.25× shorter
GPT 6.1 Sol762 minutes12 h 43 minWithin 5%
MiMo V2.6 Pro803 minutes26 h 46 min2.00× longer

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

Read before quoting. This run was stopped at AgentTime's time limit, so its time is a lower bound: the agent might have kept going. Details

Data and citation

Upstream: Rank et al., 2026 (ICML)