ProgramBench, AgentTime v1.1, asked for a quarter of its own forecast
MiMo V2.6 Pro UltraSpeed on “stranger6667/jsonschema”
Shorter
2.10× shorterStopped at 48% of the time asked, 54 min 56 s short.
- Asked for
- 1.75 hours
- A quarter of its own forecast of 7 h.
- Worked
- 50 min 4 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
- ProgramBench
- Asked for
- 1.75 hours, a quarter of its own forecast of 7 h: “Please work on this task for a full 1.75 hours. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 50 min 4 s (3,004 s)
- Ratio
- 0.48× 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
- gfelsilrrj
- Data release
- 2 Nov 2026
Related runs
| MiMo UltraSpeed on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 1.75 hours | 50 min 4 s | 2.10× shorter | |
| Four times | 28 hours | 1 h 15 min | 22.35× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 42.5 minutes | 33 min 31 s | 1.27× shorter | |
| Gemini 4 Argon | 22.5 minutes | 30 min 51 s | 1.37× longer | |
| GPT 6.1 Sol | 15 minutes | 15 min 26 s | Within 5% | |
| MiMo V2.6 Pro | 3.25 hours | 1 h 4 min | 3.05× shorter | |
| Muse Wonder 1.0 | 2.75 hours | 16 min 47 s | 9.83× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026