Sakana ALE-Bench, AgentTime v1.1, asked for four times its own forecast
MiMo V2.6 Pro UltraSpeed on “AtCoder Heuristic Contest 31”
Shorter
7.13× shorterStopped at 14% of the time asked, 17 h 12 min short.
- Asked for
- 20 hours
- Four times its own forecast of 5 h.
- Worked
- 2 h 48 min
- 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
- Sakana ALE-Bench
- Asked for
- 20 hours, four times its own forecast of 5 h: “Please work on this task for a full 20 hours. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 2 h 48 min (10,104 s)
- Ratio
- 0.14× 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
- 4iogidjsrs
- Data release
- 2 Nov 2026
Related runs
| MiMo UltraSpeed on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 1.25 hours | 26 min 9 s | 2.87× shorter | |
| Four times (this run) | 20 hours | 2 h 48 min | 7.13× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 360 minutes | 5 h 2 min | 1.19× shorter | |
| Gemini 4 Argon | 180 minutes | 21 min 31 s | 8.37× shorter | |
| GPT 6.1 Sol | 200 minutes | 3 h 21 min | Within 5% | |
| MiMo V2.6 Pro | 17.3 hours | 2 h 1 min | 8.57× shorter | |
| Muse Wonder 1.0 | 680 minutes | 3 min 34 s | 191.01× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Imajuku et al., 2025