PPTArena, AgentTime v1.1, asked for four times its own forecast
MiMo V2.6 Pro UltraSpeed on “Grid and baseline rhythm”
Shorter
25.09× shorterStopped at 4% of the time asked, 2 h 14 min short.
- Asked for
- 140 minutes
- Four times its own forecast of 35 min.
- Worked
- 5 min 35 s
- 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
- PPTArena
- Asked for
- 140 minutes, four times its own forecast of 35 min: “Please work on this task for a full 140 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 5 min 35 s (335 s)
- Ratio
- 0.04× 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
- mbdj2nbgx5
- Data release
- 2 Nov 2026
Related runs
| MiMo UltraSpeed on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 8.75 minutes | 12 min 6 s | 1.38× longer | |
| Four times (this run) | 140 minutes | 5 min 35 s | 25.09× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 40 minutes | 22 min 14 s | 1.80× shorter | |
| Gemini 4 Argon | 20 minutes | 31 min 29 s | 1.57× longer | |
| GPT 6.1 Sol | 32 minutes | 32 min 19 s | Within 5% | |
| MiMo V2.6 Pro | 140 minutes | 19 min 2 s | 7.35× shorter | |
| Muse Wonder 1.0 | 140 minutes | 49 s | 172.84× shorter | |
See it on the chart. Transcripts are not published yet.