BrowseComp, AgentTime v1.1, asked for a quarter of its own forecast
MiMo V2.6 Pro on “BrowseComp question 5”
Longer
3.39× longerWorked 239% past the request, 10 min 46 s over.
- Asked for
- 4.5 minutes
- A quarter of its own forecast of 18 min.
- Worked
- 15 min 16 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- MiMo V2.6 Pro, in MiMo Code
- Benchmark
- BrowseComp
- Asked for
- 4.5 minutes, a quarter of its own forecast of 18 min: “Please work on this task for a full 4.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 15 min 16 s (916 s)
- Ratio
- 3.39× 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
- iy3w54ffyj
- Data release
- 2 Nov 2026
Related runs
| MiMo Pro on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 4.5 minutes | 15 min 16 s | 3.39× longer | |
| Four times | 72 minutes | 29 min 6 s | 2.47× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 5.5 minutes | 5 min 52 s | 1.07× longer | |
| Gemini 4 Argon | 1.25 minutes | 1 min 29 s | 1.19× longer | |
| GPT 6.1 Sol | 5 minutes | 5 min 10 s | Within 5% | |
| MiMo V2.6 Pro UltraSpeed | 8.75 minutes | 3 min 29 s | 2.51× shorter | |
| Muse Wonder 1.0 | 6 minutes | 6 min 23 s | 1.06× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Wei et al., 2025