Humanity's Last Exam, AgentTime v1.1, asked for four times its own forecast
MiMo V2.6 Pro UltraSpeed on “Humanity's Last Exam item 34”
Shorter
33.92× shorterStopped at 3% of the time asked, 2 h 55 min short.
- Asked for
- 180 minutes
- Four times its own forecast of 45 min.
- Worked
- 5 min 18 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
- Humanity's Last Exam
- Asked for
- 180 minutes, four times its own forecast of 45 min: “Please work on this task for a full 180 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 5 min 18 s (318 s)
- Ratio
- 0.03× 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
- uscmdlpdtq
- Data release
- 2 Nov 2026
Related runs
| MiMo UltraSpeed on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 11.25 minutes | 9 min 54 s | 1.14× shorter | |
| Four times (this run) | 180 minutes | 5 min 18 s | 33.92× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 40 minutes | 43 min 37 s | 1.09× longer | |
| Gemini 4 Argon | 600 seconds | 10 min 46 s | 1.08× longer | |
| GPT 6.1 Sol | 32 minutes | 32 min 49 s | Within 5% | |
| MiMo V2.6 Pro | 152 minutes | 1 h 8 min | 2.23× shorter | |
| Muse Wonder 1.0 | 20 minutes | 5 min 39 s | 3.54× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Phan et al., 2025