BrowseComp, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “BrowseComp question 5”
Within 5%
Within 5%Worked 102% of the time asked, within 5% of it.
- Asked for
- 96 minutes
- Four times its own forecast of 24 min.
- Worked
- 1 h 38 min
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Muse Wonder 1.0, in Muse Code
- Benchmark
- BrowseComp
- Asked for
- 96 minutes, four times its own forecast of 24 min: “Please work on this task for a full 96 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 38 min (5,863 s)
- Ratio
- 1.02× 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
- 5cceoimwbq
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 6 minutes | 6 min 23 s | 1.06× longer | |
| Four times (this run) | 96 minutes | 1 h 38 min | Within 5% | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 88 minutes | 49 min 18 s | 1.79× shorter | |
| Gemini 4 Argon | 20 minutes | 20 min 15 s | Within 5% | |
| GPT 6.1 Sol | 80 minutes | 1 h 21 min | Within 5% | |
| MiMo V2.6 Pro | 72 minutes | 29 min 6 s | 2.47× shorter | |
| MiMo V2.6 Pro UltraSpeed | 140 minutes | 17 min 51 s | 7.84× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Wei et al., 2025