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× shorterStopped 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
Related runs
| MiMo UltraSpeed on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 2.19 hours | 4 h 21 min | 1.98× longer | |
| Four times (this run) | 35 hours | 12 h 53 min | 2.72× shorter | |
| Other agents, four times their own runtime | ||||
| Claude Opus 5.5 | 55.4 hours | 16 h 19 min | 3.40× shorter | |
| Gemini 4 Argon | 253 minutes | 2 h 21 min | 1.80× shorter | |
| GPT 6.1 Sol | 442 minutes | 7 h 22 min | Within 5% | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Starace et al., 2025