Humanity's Last Exam, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “Humanity's Last Exam item 36”
Shorter
1.71× shorterStopped at 59% of the time asked, 8 min 18 s short.
- Asked for
- 20 minutes
- Four times its own forecast of 5 min.
- Worked
- 11 min 42 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
- 20 minutes, four times its own forecast of 5 min: “Please work on this task for a full 20 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 11 min 42 s (702 s)
- Ratio
- 0.58× 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
- 4kpubyqfhb
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 1.25 minutes | 2 min 50 s | 2.27× longer | |
| Four times (this run) | 20 minutes | 11 min 42 s | 1.71× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 360 seconds | 6 min 23 s | 1.06× longer | |
| Gemini 4 Argon | 360 seconds | 6 min 35 s | 1.10× longer | |
| GPT 6.1 Sol | 20 minutes | 20 min 21 s | Within 5% | |
| MiMo V2.6 Pro | 48 minutes | 49 min 53 s | Within 5% | |
| MiMo V2.6 Pro UltraSpeed | 48 minutes | 10 min 51 s | 4.42× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Phan et al., 2025