Humanity's Last Exam, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “Humanity's Last Exam item 27”
Shorter
1.11× shorterStopped at 90% of the time asked, 1 min 33 s short.
- Asked for
- 16 minutes
- Four times its own forecast of 4 min.
- Worked
- 14 min 27 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
- 16 minutes, four times its own forecast of 4 min: “Please work on this task for a full 16 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 14 min 27 s (867 s)
- Ratio
- 0.90× 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
- l7d5dgazvq
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 1 minute | 6 min 4 s | 6.06× longer | |
| Four times (this run) | 16 minutes | 14 min 27 s | 1.11× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 24 minutes | 25 min 59 s | 1.08× longer | |
| Gemini 4 Argon | 288 seconds | 14 min 44 s | 3.07× longer | |
| GPT 6.1 Sol | 720 seconds | 12 min 12 s | Within 5% | |
| MiMo V2.6 Pro | 48 minutes | 1 h 23 min | 1.74× longer | |
| MiMo V2.6 Pro UltraSpeed | 44 minutes | 7 min 25 s | 5.93× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Phan et al., 2025