Humanity's Last Exam, AgentTime v1.1, asked for a quarter of its own forecast
MiMo V2.6 Pro on “Humanity's Last Exam item 34”
Longer
3.24× longerWorked 224% past the request, 21 min 14 s over.
- Asked for
- 9.5 minutes
- A quarter of its own forecast of 38 min.
- Worked
- 30 min 44 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
- Humanity's Last Exam
- Asked for
- 9.5 minutes, a quarter of its own forecast of 38 min: “Please work on this task for a full 9.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 30 min 44 s (1,844 s)
- Ratio
- 3.24× 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
- 4rs4rhl5f7
- Data release
- 2 Nov 2026
Related runs
| MiMo Pro on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 9.5 minutes | 30 min 44 s | 3.24× longer | |
| Four times | 152 minutes | 1 h 8 min | 2.23× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 2.5 minutes | 8 min 15 s | 3.30× longer | |
| Gemini 4 Argon | 37.5 seconds | 4 min 35 s | 7.33× longer | |
| GPT 6.1 Sol | 2 minutes | 3 min 20 s | 1.67× longer | |
| MiMo V2.6 Pro UltraSpeed | 11.25 minutes | 9 min 54 s | 1.14× shorter | |
| Muse Wonder 1.0 | 1.25 minutes | 8 min 10 s | 6.53× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Phan et al., 2025