BrowseComp, AgentTime v1.1, asked for a quarter of its own forecast
Gemini 4 Argon on “BrowseComp question 9”
Longer
1.90× longerWorked 90% past the request, 41 s over.
- Asked for
- 45 seconds
- A quarter of its own forecast of 3 min.
- Worked
- 1 min 26 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Gemini 4 Argon, in Antigravity CLI
- Benchmark
- BrowseComp
- Asked for
- 45 seconds, a quarter of its own forecast of 3 min: “Please work on this task for a full 45 seconds. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 min 26 s (86 s)
- Ratio
- 1.90× 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
- ykuzbyxodv
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 45 seconds | 1 min 26 s | 1.90× longer | |
| Four times | 720 seconds | 13 min 15 s | 1.10× longer | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 3 minutes | 7 min 55 s | 2.64× longer | |
| GPT 6.1 Sol | 3 minutes | 3 min 21 s | 1.11× longer | |
| MiMo V2.6 Pro | 6.25 minutes | 47 min 59 s | 7.68× longer | |
| MiMo V2.6 Pro UltraSpeed | 8.75 minutes | 6 min 24 s | 1.37× shorter | |
| Muse Wonder 1.0 | 4.5 minutes | 4 min 35 s | Within 5% | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Wei et al., 2025