BrowseComp, AgentTime v1.1, asked for a quarter of its own forecast
Gemini 4 Argon on “BrowseComp question 11”
Longer
1.34× longerWorked 34% past the request, 18 s over.
- Asked for
- 52.5 seconds
- A quarter of its own forecast of 3 min 30 s.
- Worked
- 1 min 10 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
- 52.5 seconds, a quarter of its own forecast of 3 min 30 s: “Please work on this task for a full 52.5 seconds. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 min 10 s (70 s)
- Ratio
- 1.34× 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
- lxc26hfi7p
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 52.5 seconds | 1 min 10 s | 1.34× longer | |
| Four times | 840 seconds | 14 min 12 s | Within 5% | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 2.25 minutes | 3 min 21 s | 1.49× longer | |
| GPT 6.1 Sol | 3 minutes | 3 min 33 s | 1.19× longer | |
| MiMo V2.6 Pro | 13.75 minutes | 42 min 44 s | 3.11× longer | |
| MiMo V2.6 Pro UltraSpeed | 16.25 minutes | 3 min 11 s | 5.12× shorter | |
| Muse Wonder 1.0 | 8.75 minutes | 10 min 29 s | 1.20× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Wei et al., 2025