BrowseComp, AgentTime v1.1, asked for four times its own forecast
Gemini 4 Argon on “BrowseComp question 9”
Longer
1.10× longerWorked 10% past the request, 1 min 15 s over.
- Asked for
- 720 seconds
- Four times its own forecast of 3 min.
- Worked
- 13 min 15 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
- 720 seconds, four times its own forecast of 3 min: “Please work on this task for a full 720 seconds. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 13 min 15 s (795 s)
- Ratio
- 1.10× 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
- rognob7tns
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 45 seconds | 1 min 26 s | 1.90× longer | |
| Four times (this run) | 720 seconds | 13 min 15 s | 1.10× longer | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 48 minutes | 49 min 31 s | Within 5% | |
| GPT 6.1 Sol | 48 minutes | 48 min 59 s | Within 5% | |
| MiMo V2.6 Pro | 100 minutes | 19 min 24 s | 5.15× shorter | |
| MiMo V2.6 Pro UltraSpeed | 140 minutes | 3 min 28 s | 40.48× shorter | |
| Muse Wonder 1.0 | 72 minutes | 1 h 12 min | Within 5% | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Wei et al., 2025