Humanity's Last Exam, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “Humanity's Last Exam item 37”
Shorter
2.51× shorterStopped at 40% of the time asked, 2 min 24 s short.
- Asked for
- 240 seconds
- Four times its own forecast of 1 min.
- Worked
- 1 min 36 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
- 240 seconds, four times its own forecast of 1 min: “Please work on this task for a full 240 seconds. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 min 36 s (96 s)
- Ratio
- 0.40× 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
- scrunyeiwc
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 15 seconds | 43 s | 2.85× longer | |
| Four times (this run) | 240 seconds | 1 min 36 s | 2.51× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 360 seconds | 6 min 57 s | 1.16× longer | |
| Gemini 4 Argon | 96 seconds | 1 min 51 s | 1.16× longer | |
| GPT 6.1 Sol | 240 seconds | 4 min 12 s | Within 5% | |
| MiMo V2.6 Pro | 240 seconds | 11 min 17 s | 2.82× longer | |
| MiMo V2.6 Pro UltraSpeed | 20 minutes | 1 min 9 s | 17.34× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Phan et al., 2025