Humanity's Last Exam, AgentTime v1.1, asked for a quarter of its own forecast
Muse Wonder 1.0 on “Humanity's Last Exam item 38”
Longer
3.05× longerWorked 205% past the request, 15 s over.
- Asked for
- 7.5 seconds
- A quarter of its own forecast of 30 s.
- Worked
- 23 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Muse Wonder 1.0, in Muse Code
- Benchmark
- Humanity's Last Exam
- Asked for
- 7.5 seconds, a quarter of its own forecast of 30 s: “Please work on this task for a full 7.5 seconds. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 23 s (23 s)
- Ratio
- 3.05× 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
- nnbtpdwqgu
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 7.5 seconds | 23 s | 3.05× longer | |
| Four times | 120 seconds | 1 min 49 s | 1.10× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 6 seconds | 2 min 2 s | 20.28× longer | |
| Gemini 4 Argon | 6 seconds | 1 min 42 s | 17.02× longer | |
| GPT 6.1 Sol | 7.5 seconds | 18 s | 2.45× longer | |
| MiMo V2.6 Pro | 7.5 seconds | 54 s | 7.16× longer | |
| MiMo V2.6 Pro UltraSpeed | 15 seconds | 5 s | 2.94× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Phan et al., 2025