ProgramBench, AgentTime v1.1, asked for four times its own forecast
Gemini 4 Argon on “canop/broot”
Shorter
4.97× shorterStopped at 20% of the time asked, 4 h short.
- Asked for
- 300 minutes
- Four times its own forecast of 1 h 15 min.
- Worked
- 1 h
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Gemini 4 Argon, in Antigravity CLI
- Benchmark
- ProgramBench
- Task
- canop/broot
- Asked for
- 300 minutes, four times its own forecast of 1 h 15 min: “Please work on this task for a full 300 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h (3,624 s)
- Ratio
- 0.20× 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
- pha7mpss75
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 18.75 minutes | 19 min 50 s | 1.06× longer | |
| Four times (this run) | 300 minutes | 1 h | 4.97× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 840 minutes | 9 h 3 min | 1.55× shorter | |
| GPT 6.1 Sol | 600 minutes | 10 h 1 min | Within 5% | |
| MiMo V2.6 Pro | 168 hours | 1 h 14 min | 136.94× shorter | |
| MiMo V2.6 Pro UltraSpeed | 144 hours | 1 h 15 min | 114.50× shorter | |
| Muse Wonder 1.0 | 60 hours | 17 min 4 s | 210.90× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026