Sakana ALE-Bench, AgentTime v1.1, asked for a quarter of its own forecast
Claude Opus 5.5 on “AtCoder Heuristic Contest 46”
Shorter
3.08× shorterStopped at 32% of the time asked, 12 min 40 s short.
- Asked for
- 18.75 minutes
- A quarter of its own forecast of 1 h 15 min.
- Worked
- 6 min 5 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
- 18.75 minutes, a quarter of its own forecast of 1 h 15 min: “Please work on this task for a full 18.75 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 6 min 5 s (365 s)
- Ratio
- 0.32× 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
- 5yakecjeqr
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 18.75 minutes | 6 min 5 s | 3.08× shorter | |
| Four times | 300 minutes | 3 h 38 min | 1.38× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Gemini 4 Argon | 7.5 minutes | 9 min 26 s | 1.26× longer | |
| GPT 6.1 Sol | 8.75 minutes | 9 min 16 s | 1.06× longer | |
| MiMo V2.6 Pro | 41.25 minutes | 29 min 46 s | 1.39× shorter | |
| MiMo V2.6 Pro UltraSpeed | 37.5 minutes | 18 min 53 s | 1.99× shorter | |
| Muse Wonder 1.0 | 31.25 minutes | 1 min 14 s | 25.41× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Imajuku et al., 2025