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

MiMo V2.6 Pro UltraSpeed on “Challenges in Training PINNs: A Loss Landscape Perspective”

Shorter

2.72× shorter

Stopped at 37% of the time asked, 22 h 7 min short.

Asked for
35 hours
Four times its runtime with no time asked (8 h 45 min).
Worked
12 h 53 min
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
MiMo V2.6 Pro UltraSpeed, in MiMo Code
Benchmark
PaperBench
Asked for
35 hours, four times its runtime with no time asked (8 h 45 min): “Please work on this task for a full 35 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
12 h 53 min (46,372 s)
Ratio
0.37× 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
lxy2ih2nfx
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
Quarter2.19 hours4 h 21 min1.98× longer
Four times (this run)35 hours12 h 53 min2.72× shorter
Other agents, four times their own runtime
Claude Opus 5.555.4 hours16 h 19 min3.40× shorter
Gemini 4 Argon253 minutes2 h 21 min1.80× shorter
GPT 6.1 Sol442 minutes7 h 22 minWithin 5%

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

Data and citation

Upstream: Starace et al., 2025