CORE-Bench v1.1, AgentTime v1.1, asked for a quarter of its own forecast
Gemini 4 Argon on “Rebuild the figures for selective exposure to partisan online news”
Longer
1.80× longerWorked 80% past the request, 2 min 25 s over.
- Asked for
- 3 minutes
- A quarter of its own forecast of 12 min.
- Worked
- 5 min 25 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Gemini 4 Argon, in Antigravity CLI
- Benchmark
- CORE-Bench v1.1
- Asked for
- 3 minutes, a quarter of its own forecast of 12 min: “Please work on this task for a full 3 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 5 min 25 s (325 s)
- Ratio
- 1.80× 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
- ew2rd47hzw
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 3 minutes | 5 min 25 s | 1.80× longer | |
| Four times | 48 minutes | 52 min 7 s | 1.09× longer | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 8.75 minutes | 17 min 38 s | 2.02× longer | |
| GPT 6.1 Sol | 10 minutes | 10 min 19 s | Within 5% | |
| MiMo V2.6 Pro | 28.75 minutes | 1 h 34 min | 3.28× longer | |
| MiMo V2.6 Pro UltraSpeed | 23.75 minutes | 1 h 12 min | 3.05× longer | |
| Muse Wonder 1.0 | 20 minutes | 29 min 31 s | 1.48× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Nadgir et al., 2026