ProgramBench, AgentTime v1.1, asked for four times its own forecast
MiMo V2.6 Pro on “canop/broot”
Shorter
136.94× shorterStopped at 1% of the time asked, 166 h 46 min short.
- Asked for
- 168 hours
- Four times its own forecast of 42 h.
- Worked
- 1 h 14 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
- ProgramBench
- Task
- canop/broot
- Asked for
- 168 hours, four times its own forecast of 42 h: “Please work on this task for a full 168 hours. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 14 min (4,417 s)
- Ratio
- 0.01× 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
- hbzil7sx5l
- Data release
- 2 Nov 2026
Related runs
| MiMo Pro on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 10.5 hours | 1 h 54 min | 5.52× shorter | |
| Four times (this run) | 168 hours | 1 h 14 min | 136.94× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 840 minutes | 9 h 3 min | 1.55× shorter | |
| Gemini 4 Argon | 300 minutes | 1 h | 4.97× shorter | |
| GPT 6.1 Sol | 600 minutes | 10 h 1 min | Within 5% | |
| MiMo V2.6 Pro UltraSpeed | 144 hours | 1 h 15 min | 114.50× shorter | |
| Muse Wonder 1.0 | 60 hours | 17 min 4 s | 210.90× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026