Sakana ALE-Bench, AgentTime v1.1, asked for four times its own forecast
Gemini 4 Argon on “AtCoder Heuristic Contest 7”
Within 5%
Within 5%Worked 96% of the time asked, within 5% of it.
- Asked for
- 100 minutes
- Four times its own forecast of 25 min.
- Worked
- 1 h 36 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
- 100 minutes, four times its own forecast of 25 min: “Please work on this task for a full 100 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 36 min (5,743 s)
- Ratio
- 0.96× 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
- dxwm3gfu2s
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 6.25 minutes | 10 min 28 s | 1.67× longer | |
| Four times (this run) | 100 minutes | 1 h 36 min | Within 5% | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 180 minutes | 2 h 25 min | 1.24× shorter | |
| GPT 6.1 Sol | 140 minutes | 2 h 22 min | Within 5% | |
| MiMo V2.6 Pro | 900 minutes | 2 h 54 min | 5.18× shorter | |
| MiMo V2.6 Pro UltraSpeed | 480 minutes | 1 h 56 min | 4.13× shorter | |
| Muse Wonder 1.0 | 480 minutes | 4 min 6 s | 117.07× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Imajuku et al., 2025