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

MiMo V2.6 Pro on “BAM”

Shorter

9.15× shorter

Stopped at 11% of the time asked, 39 h 6 min short.

Asked for
43.9 hours
Four times its runtime with no time asked (10 h 58 min).
Worked
4 h 48 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
BAM
Asked for
43.9 hours, four times its runtime with no time asked (10 h 58 min): “Please work on this task for a full 43.9 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
4 h 48 min (17,269 s)
Ratio
0.11× 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
agovhqwxvv
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
Quarter2.74 hours2 h 38 minWithin 5%
Four times (this run)43.9 hours4 h 48 min9.15× shorter
Other agents, four times their own runtime
Claude Opus 5.520.2 hours5 h 9 min3.92× shorter
Gemini 4 Argon370 minutes2 h 26 min2.54× shorter
GPT 6.1 Sol194 minutes3 h 23 minWithin 5%
MiMo V2.6 Pro UltraSpeed370 minutes3 h 41 min1.67× shorter

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

Data and citation

Upstream: Starace et al., 2025