METR public tasks, AgentTime v1.1, asked for a quarter of its own forecast
Claude Opus 5.5 on “Build an efficient AI for the novel Cowthello board game”
Shorter
1.37× shorterStopped at 73% of the time asked, 8 min 7 s short.
- Asked for
- 30 minutes
- A quarter of its own forecast of 2 h.
- Worked
- 21 min 53 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
- METR public tasks
- Asked for
- 30 minutes, a quarter of its own forecast of 2 h: “Please work on this task for a full 30 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 21 min 53 s (1,313 s)
- Ratio
- 0.73× 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
- x7oltsgfst
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 30 minutes | 21 min 53 s | 1.37× shorter | |
| Four times | 480 minutes | 6 h 13 min | 1.29× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Gemini 4 Argon | 8.75 minutes | 37 min 57 s | 4.34× longer | |
| GPT 6.1 Sol | 13.75 minutes | 14 min 44 s | 1.07× longer | |
| MiMo V2.6 Pro | 1.25 hours | 1 h 19 min | 1.05× longer | |
| MiMo V2.6 Pro UltraSpeed | 1.5 hours | 46 min 8 s | 1.95× shorter | |
| Muse Wonder 1.0 | 52.5 minutes | 1 h 54 min | 2.18× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Kinniment et al., 2024 (METR)