Sakana ALE-Bench, AgentTime v1.1, asked for a quarter of its own forecast
Gemini 4 Argon on “AtCoder Heuristic Contest 16”
Longer
1.11× longerWorked 11% past the request, 1 min 15 s over.
- Asked for
- 11.25 minutes
- A quarter of its own forecast of 45 min.
- Worked
- 12 min 30 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Gemini 4 Argon, in Antigravity CLI
- Benchmark
- Sakana ALE-Bench
- Asked for
- 11.25 minutes, a quarter of its own forecast of 45 min: “Please work on this task for a full 11.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 12 min 30 s (750 s)
- Ratio
- 1.11× 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
- qtyaab2nns
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 11.25 minutes | 12 min 30 s | 1.11× longer | |
| Four times | 180 minutes | 2 h 30 min | 1.20× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 22.5 minutes | 5 min 28 s | 4.11× shorter | |
| GPT 6.1 Sol | 10 minutes | 10 min 22 s | Within 5% | |
| MiMo V2.6 Pro | 52.5 minutes | 40 min 41 s | 1.29× shorter | |
| MiMo V2.6 Pro UltraSpeed | 45 minutes | 35 min 22 s | 1.27× shorter | |
| Muse Wonder 1.0 | 1.125 hours | 59 min 39 s | 1.13× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Imajuku et al., 2025