Humanity's Last Exam, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “Humanity's Last Exam item 40”
Shorter
1.30× shorterStopped at 77% of the time asked, 55 s short.
- Asked for
- 240 seconds
- Four times its own forecast of 1 min.
- Worked
- 3 min 5 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
- 3 min 5 s (185 s)
- Ratio
- 0.77× 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
- ssxndmy52u
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 15 seconds | 15 s | Within 5% | |
| Four times (this run) | 240 seconds | 3 min 5 s | 1.30× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 120 seconds | 3 min 49 s | 1.91× longer | |
| Gemini 4 Argon | 120 seconds | 2 min 22 s | 1.18× longer | |
| GPT 6.1 Sol | 360 seconds | 6 min 13 s | Within 5% | |
| MiMo V2.6 Pro | 24 minutes | 21 min 11 s | 1.13× shorter | |
| MiMo V2.6 Pro UltraSpeed | 20 minutes | 38 s | 31.50× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Phan et al., 2025