BrowseComp, AgentTime v1.1, asked for four times its own forecast
MiMo V2.6 Pro UltraSpeed on “BrowseComp question 7”
Shorter
35.26× shorterStopped at 3% of the time asked, 2 h 16 min short.
- Asked for
- 140 minutes
- Four times its own forecast of 35 min.
- Worked
- 3 min 58 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- MiMo V2.6 Pro UltraSpeed, in MiMo Code
- Benchmark
- BrowseComp
- Asked for
- 140 minutes, four times its own forecast of 35 min: “Please work on this task for a full 140 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 3 min 58 s (238 s)
- Ratio
- 0.03× 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
- j4kv6nvfmm
- Data release
- 2 Nov 2026
Related runs
| MiMo UltraSpeed on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 8.75 minutes | 14 min 24 s | 1.64× longer | |
| Four times (this run) | 140 minutes | 3 min 58 s | 35.26× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 20 minutes | 21 min 1 s | 1.05× longer | |
| Gemini 4 Argon | 480 seconds | 8 min 29 s | 1.06× longer | |
| GPT 6.1 Sol | 24 minutes | 24 min 18 s | Within 5% | |
| MiMo V2.6 Pro | 120 minutes | 40 min 10 s | 2.99× shorter | |
| Muse Wonder 1.0 | 96 minutes | 1 min 55 s | 50.04× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Wei et al., 2025