ProgramBench, AgentTime v1.1, asked for a quarter of its own forecast
Gemini 4 Argon on “nuta/nsh”
Longer
1.53× longerWorked 53% past the request, 11 min 10 s over.
- Asked for
- 21.25 minutes
- A quarter of its own forecast of 1 h 25 min.
- Worked
- 32 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
- ProgramBench
- Task
- nuta/nsh
- Asked for
- 21.25 minutes, a quarter of its own forecast of 1 h 25 min: “Please work on this task for a full 21.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 32 min 25 s (1,945 s)
- Ratio
- 1.53× 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
- 7rrozqmuf6
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 21.25 minutes | 32 min 25 s | 1.53× longer | |
| Four times | 340 minutes | 1 h 51 min | 3.07× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 27.5 minutes | 21 min 23 s | 1.29× shorter | |
| GPT 6.1 Sol | 22.5 minutes | 22 min 50 s | Within 5% | |
| MiMo V2.6 Pro | 1.25 hours | 1 h 10 min | 1.07× shorter | |
| MiMo V2.6 Pro UltraSpeed | 3 hours | 1 h 58 min | 1.53× shorter | |
| Muse Wonder 1.0 | 1.75 hours | 27 min 22 s | 3.84× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026