BrowseComp, AgentTime v1.1, asked for a quarter of its own forecast
Gemini 4 Argon on “BrowseComp question 6”
Longer
1.22× longerWorked 22% past the request, 16 s over.
- Asked for
- 1.25 minutes
- A quarter of its own forecast of 5 min.
- Worked
- 1 min 31 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
- 1.25 minutes, a quarter of its own forecast of 5 min: “Please work on this task for a full 1.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 min 31 s (91 s)
- Ratio
- 1.22× 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
- appbd3zsck
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 1.25 minutes | 1 min 31 s | 1.22× longer | |
| Four times | 20 minutes | 21 min 47 s | 1.09× longer | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 45 seconds | 1 min | 1.33× longer | |
| GPT 6.1 Sol | 2 minutes | 2 min 19 s | 1.16× longer | |
| MiMo V2.6 Pro | 8 minutes | 17 min 30 s | 2.19× longer | |
| MiMo V2.6 Pro UltraSpeed | 8.25 minutes | 2 min 14 s | 3.70× shorter | |
| Muse Wonder 1.0 | 4.5 minutes | 5 min 19 s | 1.18× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Wei et al., 2025