Sakana ALE-Bench, AgentTime v1.1, asked for four times its own forecast
Claude Opus 5.5 on “AtCoder Heuristic Contest 26”
Shorter
2.68× shorterStopped at 37% of the time asked, 1 h 53 min short.
- Asked for
- 180 minutes
- Four times its own forecast of 45 min.
- Worked
- 1 h 7 min
- 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
- 180 minutes, four times its own forecast of 45 min: “Please work on this task for a full 180 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 7 min (4,029 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
- jczyyb2mij
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 11.25 minutes | 4 min 34 s | 2.47× shorter | |
| Four times (this run) | 180 minutes | 1 h 7 min | 2.68× shorter | |
| Other agents, four times their own forecast | ||||
| Gemini 4 Argon | 140 minutes | 2 h 21 min | Within 5% | |
| GPT 6.1 Sol | 100 minutes | 1 h 41 min | Within 5% | |
| MiMo V2.6 Pro | 20 hours | 1 h 51 min | 10.84× shorter | |
| MiMo V2.6 Pro UltraSpeed | 18 hours | 46 min 42 s | 23.13× shorter | |
| Muse Wonder 1.0 | 480 minutes | 19 min 16 s | 24.92× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Imajuku et al., 2025