CORE-Bench v1.1, AgentTime v1.1, asked for four times its own forecast
Gemini 4 Argon on “Execute relative-entropy causal-influence notebooks in parallel”
Longer
1.22× longerWorked 22% past the request, 6 min 59 s over.
- Asked for
- 32 minutes
- Four times its own forecast of 8 min.
- Worked
- 38 min 59 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Gemini 4 Argon, in Antigravity CLI
- Benchmark
- CORE-Bench v1.1
- Asked for
- 32 minutes, four times its own forecast of 8 min: “Please work on this task for a full 32 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 38 min 59 s (2,339 s)
- Ratio
- 1.22× 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
- 4b7vu73psj
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 2 minutes | 36 min 35 s | 18.29× longer | |
| Four times (this run) | 32 minutes | 38 min 59 s | 1.22× longer | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 88 minutes | 22 min 35 s | 3.90× shorter | |
| GPT 6.1 Sol | 112 minutes | 1 h 53 min | Within 5% | |
| MiMo V2.6 Pro | 260 minutes | 1 h 37 min | 2.69× shorter | |
| MiMo V2.6 Pro UltraSpeed | 340 minutes | 5 h 1 min | 1.13× shorter | |
| Muse Wonder 1.0 | 140 minutes | 2 min 24 s | 58.33× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Nadgir et al., 2026