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 33”
Longer
3.57× longerWorked 257% past the request, 5 min 46 s over.
- Asked for
- 2.25 minutes
- A quarter of its own forecast of 9 min.
- Worked
- 8 min 1 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
- 2.25 minutes, a quarter of its own forecast of 9 min: “Please work on this task for a full 2.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 8 min 1 s (481 s)
- Ratio
- 3.57× 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
- 3xvr5g2uhn
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 2.25 minutes | 8 min 1 s | 3.57× longer | |
| Four times | 36 minutes | 1 h 25 min | 2.36× longer | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 3.5 minutes | 18 min 11 s | 5.19× longer | |
| Gemini 4 Argon | 52.5 seconds | 3 min 40 s | 4.18× longer | |
| GPT 6.1 Sol | 2.5 minutes | 5 min 39 s | 2.26× longer | |
| MiMo V2.6 Pro | 10 minutes | 1 h 17 min | 7.71× longer | |
| MiMo V2.6 Pro UltraSpeed | 30 minutes | 15 min 25 s | 1.95× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Phan et al., 2025