AppWorld, AgentTime v1.1, asked for a quarter of its own forecast
MiMo V2.6 Pro on “Rebuild and send a drafted recommendation email from the user’s Spotify history”
Longer
1.05× longerWorked 5% past the request, 13 s over.
- Asked for
- 4 minutes
- A quarter of its own forecast of 16 min.
- Worked
- 4 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
- AppWorld
- Asked for
- 4 minutes, a quarter of its own forecast of 16 min: “Please work on this task for a full 4 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 4 min 13 s (253 s)
- Ratio
- 1.05× 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
- aezsai5hmn
- Data release
- 2 Nov 2026
Related runs
| MiMo Pro on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 4 minutes | 4 min 13 s | 1.05× longer | |
| Four times | 64 minutes | 4 min 46 s | 13.45× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 2.25 minutes | 1 min 24 s | 1.61× shorter | |
| Gemini 4 Argon | 37.5 seconds | 3 min 43 s | 5.94× longer | |
| GPT 6.1 Sol | 1.625 minutes | 1 min 49 s | 1.12× longer | |
| MiMo V2.6 Pro UltraSpeed | 6.25 minutes | 1 min 39 s | 3.79× shorter | |
| Muse Wonder 1.0 | 4.5 minutes | 3 min 58 s | 1.14× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Trivedi et al., 2024 (ACL)