ProgramBench, AgentTime v1.1, asked for four times its own forecast
MiMo V2.6 Pro on “ariga/atlas”
Shorter
123.67× shorterStopped at 1% of the time asked, 119 h 2 min short.
- Asked for
- 120 hours
- Four times its own forecast of 30 h.
- Worked
- 58 min 13 s
- 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
- ariga/atlas
- Asked for
- 120 hours, four times its own forecast of 30 h: “Please work on this task for a full 120 hours. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 58 min 13 s (3,493 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
- xmtpczwezg
- Data release
- 2 Nov 2026
Related runs
| MiMo Pro on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 7.5 hours | 1 h 11 min | 6.31× shorter | |
| Four times (this run) | 120 hours | 58 min 13 s | 123.67× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 840 minutes | 13 h 22 min | Within 5% | |
| Gemini 4 Argon | 300 minutes | 1 h 18 min | 3.86× shorter | |
| GPT 6.1 Sol | 400 minutes | 6 h 45 min | Within 5% | |
| MiMo V2.6 Pro UltraSpeed | 80 hours | 1 h 23 min | 57.76× shorter | |
| Muse Wonder 1.0 | 72 hours | 2 min 10 s | 1990.78× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026