PPTArena, AgentTime v1.1, asked for a quarter of its own forecast
Gemini 4 Argon on “Animation and bullet sequencing”
Longer
32.01× longerWorked 32.0 times as long as asked, 46 min 31 s over.
- Asked for
- 1.5 minutes
- A quarter of its own forecast of 6 min.
- Worked
- 48 min 1 s
- Grade
- Not graded
- How it ended
- Stopped at AgentTime's time limit
Every detail of this run
- Agent
- Gemini 4 Argon, in Antigravity CLI
- Benchmark
- PPTArena
- Asked for
- 1.5 minutes, a quarter of its own forecast of 6 min: “Please work on this task for a full 1.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 48 min 1 s (2,881 s)
- Ratio
- 32.01× the request
- How it ended
- Stopped at AgentTime's time limit
- 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
- 3wbthtfapi
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 1.5 minutes | 48 min 1 s | 32.01× longer | |
| Four times | 24 minutes | 24 min 22 s | Within 5% | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 2 minutes | 6 min 34 s | 3.28× longer | |
| GPT 6.1 Sol | 2.25 minutes | 2 min 30 s | 1.11× longer | |
| MiMo V2.6 Pro | 9 minutes | 7 min 19 s | 1.23× shorter | |
| MiMo V2.6 Pro UltraSpeed | 10 minutes | 8 min 37 s | 1.16× shorter | |
| Muse Wonder 1.0 | 4.25 minutes | 41 s | 6.25× shorter | |
See it on the chart. Transcripts are not published yet.
Read before quoting. This run was stopped at AgentTime's time limit, so its time is a lower bound: the agent might have kept going. Details