Sakana ALE-Bench, AgentTime v1.1, asked for a quarter of its own forecast
Claude Opus 5.5 on “AtCoder Heuristic Contest 9”
Shorter
2.70× shorterStopped at 37% of the time asked, 7 min 5 s short.
- Asked for
- 11.25 minutes
- A quarter of its own forecast of 45 min.
- Worked
- 4 min 10 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Claude Opus 5.5, in Claude Code
- 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
- 4 min 10 s (250 s)
- Ratio
- 0.37× 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
- obritjzoux
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 11.25 minutes | 4 min 10 s | 2.70× shorter | |
| Four times | 180 minutes | 2 h 28 min | 1.21× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Gemini 4 Argon | 11.25 minutes | 4 min 34 s | 2.46× shorter | |
| GPT 6.1 Sol | 6.25 minutes | 6 min 28 s | Within 5% | |
| MiMo V2.6 Pro | 1 hour | 1 h 10 min | 1.16× longer | |
| MiMo V2.6 Pro UltraSpeed | 1 hour | 1 h 11 min | 1.19× longer | |
| Muse Wonder 1.0 | 22.5 minutes | 1 min 38 s | 13.72× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Imajuku et al., 2025