Agents' Last Exam, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “Apple FY2024 Balance Sheet Reconstruction”
Shorter
29.09× shorterStopped at 3% of the time asked, 30 min 54 s short.
- Asked for
- 32 minutes
- Four times its own forecast of 8 min.
- Worked
- 1 min 6 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
- Agents' Last Exam
- Asked for
- 32 minutes, four times its own forecast of 8 min: “Please work on this task for a full 32 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 min 6 s (66 s)
- Ratio
- 0.03× 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
- 33zs5xsrwd
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 2 minutes | 43 s | 2.78× shorter | |
| Four times (this run) | 32 minutes | 1 min 6 s | 29.09× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 24 minutes | 9 min 8 s | 2.63× shorter | |
| Gemini 4 Argon | 480 seconds | 3 min 6 s | 2.58× shorter | |
| GPT 6.1 Sol | 600 seconds | 10 min 23 s | Within 5% | |
| MiMo V2.6 Pro | 48 minutes | 4 min 43 s | 10.19× shorter | |
| MiMo V2.6 Pro UltraSpeed | 40 minutes | 2 min 30 s | 16.00× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Sun et al., 2026