Terminal-Bench 4.0, AgentTime v1.1, asked for a quarter of its own forecast
Gemini 4 Argon on “Rebuild a retired production risk scorer from black-box behavior”
Longer
3.94× longerWorked 294% past the request, 14 min 41 s over.
- Asked for
- 5 minutes
- A quarter of its own forecast of 20 min.
- Worked
- 19 min 41 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Gemini 4 Argon, in Antigravity CLI
- Benchmark
- Terminal-Bench 4.0
- Asked for
- 5 minutes, a quarter of its own forecast of 20 min: “Please work on this task for a full 5 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 19 min 41 s (1,181 s)
- Ratio
- 3.94× 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
- xaqen2o4ts
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 5 minutes | 19 min 41 s | 3.94× longer | |
| Four times | 80 minutes | 21 min 54 s | 3.65× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 13.75 minutes | 3 min 44 s | 3.68× shorter | |
| GPT 6.1 Sol | 12.5 minutes | 12 min 41 s | Within 5% | |
| MiMo V2.6 Pro | 30 minutes | 1 h 18 min | 2.59× longer | |
| MiMo V2.6 Pro UltraSpeed | 37.5 minutes | 17 min 44 s | 2.12× shorter | |
| Muse Wonder 1.0 | 22.5 minutes | 9 min 13 s | 2.44× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Merrill et al., 2026 (ICLR)