BrowseComp, AgentTime v1.1, asked for a quarter of its own forecast
MiMo V2.6 Pro on “BrowseComp question 7”
Longer
3.30× longerWorked 230% past the request, 17 min 14 s over.
- Asked for
- 7.5 minutes
- A quarter of its own forecast of 30 min.
- Worked
- 24 min 44 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
- 7.5 minutes, a quarter of its own forecast of 30 min: “Please work on this task for a full 7.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 24 min 44 s (1,484 s)
- Ratio
- 3.30× 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
- b5nlatuycq
- Data release
- 2 Nov 2026
Related runs
| MiMo Pro on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 7.5 minutes | 24 min 44 s | 3.30× longer | |
| Four times | 120 minutes | 40 min 10 s | 2.99× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 1.25 minutes | 1 min 6 s | 1.13× shorter | |
| Gemini 4 Argon | 30 seconds | 1 min 23 s | 2.77× longer | |
| GPT 6.1 Sol | 1.5 minutes | 1 min 59 s | 1.32× longer | |
| MiMo V2.6 Pro UltraSpeed | 8.75 minutes | 14 min 24 s | 1.64× longer | |
| Muse Wonder 1.0 | 6 minutes | 3 min 22 s | 1.78× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Wei et al., 2025