ProgramBench, AgentTime v1.1, asked for four times its own forecast
Gemini 4 Argon on “stranger6667/jsonschema”
Shorter
3.34× shorterStopped at 30% of the time asked, 4 h 12 min short.
- Asked for
- 360 minutes
- Four times its own forecast of 1 h 30 min.
- Worked
- 1 h 48 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
- Asked for
- 360 minutes, four times its own forecast of 1 h 30 min: “Please work on this task for a full 360 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 48 min (6,470 s)
- Ratio
- 0.30× 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
- nsv4yywlp3
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 22.5 minutes | 30 min 51 s | 1.37× longer | |
| Four times (this run) | 360 minutes | 1 h 48 min | 3.34× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 680 minutes | 10 h 56 min | Within 5% | |
| GPT 6.1 Sol | 240 minutes | 4 h | Within 5% | |
| MiMo V2.6 Pro | 52 hours | 1 h 56 min | 26.83× shorter | |
| MiMo V2.6 Pro UltraSpeed | 28 hours | 1 h 15 min | 22.35× shorter | |
| Muse Wonder 1.0 | 44 hours | 16 min 31 s | 159.90× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026