BrowseComp, AgentTime v1.1, asked for four times its own forecast
Gemini 4 Argon on “BrowseComp question 12”
Longer
1.19× longerWorked 19% past the request, 3 min 6 s over.
- Asked for
- 16 minutes
- Four times its own forecast of 4 min.
- Worked
- 19 min 6 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
- 16 minutes, four times its own forecast of 4 min: “Please work on this task for a full 16 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 19 min 6 s (1,146 s)
- Ratio
- 1.19× 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
- okwm6lnolx
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 1 minute | 1 min 28 s | 1.47× longer | |
| Four times (this run) | 16 minutes | 19 min 6 s | 1.19× longer | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 48 minutes | 56 min 57 s | 1.19× longer | |
| GPT 6.1 Sol | 48 minutes | 48 min 53 s | Within 5% | |
| MiMo V2.6 Pro | 180 minutes | 58 min 51 s | 3.06× shorter | |
| 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