ProgramBench, AgentTime v1.1, asked for four times its own forecast
Gemini 4 Argon on “johnkerl/miller”
Shorter
4.48× shorterStopped at 22% of the time asked, 6 h 13 min short.
- Asked for
- 480 minutes
- Four times its own forecast of 2 h.
- Worked
- 1 h 47 min
- 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
- johnkerl/miller
- Asked for
- 480 minutes, four times its own forecast of 2 h: “Please work on this task for a full 480 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 47 min (6,430 s)
- Ratio
- 0.22× 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
- bzkohiblge
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 30 minutes | 46 min 32 s | 1.55× longer | |
| Four times (this run) | 480 minutes | 1 h 47 min | 4.48× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 20 hours | 9 h 42 min | 2.06× shorter | |
| GPT 6.1 Sol | 480 minutes | 8 h 1 min | Within 5% | |
| MiMo V2.6 Pro | 40 hours | 54 min 12 s | 44.28× shorter | |
| MiMo V2.6 Pro UltraSpeed | 160 hours | 4 h 35 min | 34.90× shorter | |
| Muse Wonder 1.0 | 73.3 hours | 19 min 53 s | 221.12× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026