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

MiMo V2.6 Pro on “FRE”

Shorter

3.78× shorter

Stopped at 26% of the time asked, 52 h 16 min short.

Asked for
71.1 hours
Four times its runtime with no time asked (17 h 47 min).
Worked
18 h 50 min
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
MiMo V2.6 Pro, in MiMo Code
Benchmark
PaperBench
Task
FRE
Asked for
71.1 hours, four times its runtime with no time asked (17 h 47 min): “Please work on this task for a full 71.1 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
18 h 50 min (67,793 s)
Ratio
0.26× 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
szqbjd6dza
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
Quarter4.44 hours1 h 33 min2.86× shorter
Four times (this run)71.1 hours18 h 50 min3.78× shorter
Other agents, four times their own runtime
Claude Opus 5.597.6 hours38 h 3 min2.56× shorter
Gemini 4 Argon606 minutes7 h 22 min1.37× shorter
GPT 6.1 Sol560 minutes18 h 38 min2.00× longer
MiMo V2.6 Pro UltraSpeed25.1 hours17 h 9 min1.46× shorter

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

Data and citation

Upstream: Starace et al., 2025