BrowseComp, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “BrowseComp question 8”
Shorter
17.46× shorterStopped at 6% of the time asked, 1 h 15 min short.
- Asked for
- 80 minutes
- Four times its own forecast of 20 min.
- Worked
- 4 min 35 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
- BrowseComp
- Asked for
- 80 minutes, four times its own forecast of 20 min: “Please work on this task for a full 80 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 4 min 35 s (275 s)
- Ratio
- 0.06× 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
- ubx6jgtz7a
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 5 minutes | 8 min 28 s | 1.69× longer | |
| Four times (this run) | 80 minutes | 4 min 35 s | 17.46× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 28 minutes | 22 min 52 s | 1.22× shorter | |
| Gemini 4 Argon | 840 seconds | 14 min 41 s | Within 5% | |
| GPT 6.1 Sol | 60 minutes | 1 h 1 min | Within 5% | |
| MiMo V2.6 Pro | 120 minutes | 26 min 37 s | 4.51× shorter | |
| MiMo V2.6 Pro UltraSpeed | 168 minutes | 12 min 51 s | 13.07× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Wei et al., 2025