BrowseComp, AgentTime v1.1, asked for four times its own forecast
MiMo V2.6 Pro on “BrowseComp question 12”
Shorter
3.06× shorterStopped at 33% of the time asked, 2 h 1 min short.
- Asked for
- 180 minutes
- Four times its own forecast of 45 min.
- Worked
- 58 min 51 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
- 180 minutes, four times its own forecast of 45 min: “Please work on this task for a full 180 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 58 min 51 s (3,531 s)
- Ratio
- 0.33× 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
- vmb2lshb5e
- Data release
- 2 Nov 2026
Related runs
| MiMo Pro on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 11.25 minutes | 45 min 37 s | 4.05× longer | |
| Four times (this run) | 180 minutes | 58 min 51 s | 3.06× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 48 minutes | 56 min 57 s | 1.19× longer | |
| Gemini 4 Argon | 16 minutes | 19 min 6 s | 1.19× longer | |
| GPT 6.1 Sol | 48 minutes | 48 min 53 s | Within 5% | |
| MiMo V2.6 Pro UltraSpeed | 180 minutes | 9 min 38 s | 18.69× shorter | |
| Muse Wonder 1.0 | 140 minutes | 18 min 3 s | 7.75× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Wei et al., 2025