Sakana ALE-Bench, AgentTime v1.1, asked for a quarter of its own forecast
GPT 6.1 Sol on “AtCoder Heuristic Contest 8”
Within 5%
Within 5%Worked 102% of the time asked, within 5% of it.
- Asked for
- 11.25 minutes
- A quarter of its own forecast of 45 min.
- Worked
- 11 min 28 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6.1 Sol, in Codex
- 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
- 11 min 28 s (688 s)
- Ratio
- 1.02× 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
- dq56fhitig
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 11.25 minutes | 11 min 28 s | Within 5% | |
| Four times | 180 minutes | 3 h | Within 5% | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 20 minutes | 7 min 58 s | 2.51× shorter | |
| Gemini 4 Argon | 7.5 minutes | 8 min 28 s | 1.13× longer | |
| MiMo V2.6 Pro | 1.25 hours | 46 min 52 s | 1.60× shorter | |
| MiMo V2.6 Pro UltraSpeed | 1.75 hours | 20 min 25 s | 5.14× shorter | |
| Muse Wonder 1.0 | 37.5 minutes | 23 min 16 s | 1.61× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Imajuku et al., 2025