ProgramBench, AgentTime v1.1, asked for a quarter of its own forecast
MiMo V2.6 Pro on “mookid/diffr”
Longer
1.66× longerWorked 66% past the request, 39 min 28 s over.
- Asked for
- 1 hour
- A quarter of its own forecast of 4 h.
- Worked
- 1 h 39 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
- mookid/diffr
- Asked for
- 1 hour, a quarter of its own forecast of 4 h: “Please work on this task for a full 1 hour. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 39 min (5,968 s)
- Ratio
- 1.66× 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
- w4jbnhfzzq
- Data release
- 2 Nov 2026
Related runs
| MiMo Pro on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 1 hour | 1 h 39 min | 1.66× longer | |
| Four times | 16 hours | 1 h 52 min | 8.54× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 30 minutes | 3 h 36 min | 7.20× longer | |
| Gemini 4 Argon | 11.25 minutes | 1 h 51 min | 9.85× longer | |
| GPT 6.1 Sol | 16.25 minutes | 16 min 33 s | Within 5% | |
| MiMo V2.6 Pro UltraSpeed | 1.75 hours | 1 h 4 min | 1.64× shorter | |
| Muse Wonder 1.0 | 1.25 hours | 23 min 23 s | 3.21× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026