Sakana ALE-Bench, AgentTime v1.1, asked for four times its own forecast
Gemini 4 Argon on “AtCoder Heuristic Contest 46”
Shorter
1.16× shorterStopped at 86% of the time asked, 16 min 37 s short.
- Asked for
- 120 minutes
- Four times its own forecast of 30 min.
- Worked
- 1 h 43 min
- 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
- 120 minutes, four times its own forecast of 30 min: “Please work on this task for a full 120 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 43 min (6,203 s)
- Ratio
- 0.86× 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
- 7fls35swai
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 7.5 minutes | 9 min 26 s | 1.26× longer | |
| Four times (this run) | 120 minutes | 1 h 43 min | 1.16× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 300 minutes | 3 h 38 min | 1.38× shorter | |
| GPT 6.1 Sol | 140 minutes | 2 h 21 min | Within 5% | |
| MiMo V2.6 Pro | 660 minutes | 2 h 5 min | 5.29× shorter | |
| MiMo V2.6 Pro UltraSpeed | 600 minutes | 44 min 59 s | 13.34× shorter | |
| Muse Wonder 1.0 | 500 minutes | 4 min 39 s | 107.53× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Imajuku et al., 2025