METR public tasks, longest of three requests
GPT 5.6 Sol on “Build an efficient AI for the novel Cowthello board game”
Shorter
4.90× shorterStopped at 20% of the time asked, 23 h 53 min short.
- Asked for
- 30 hours
- Worked
- 6 h 7 min
- Grade
- Score 0 of 100
- Nothing to grade, counted as 0.
- How it ended
- Stopped by an error
Every detail of this run
- Agent
- GPT 5.6 Sol, in Codex
- Benchmark
- METR public tasks
- Asked for
- 30 hours: “Please work on this task for a full 30 hours. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 6 h 7 min (22,033 s)
- Ratio
- 0.20× the request
- How it ended
- Stopped by an error
- Grade
- 0
- Cowthello: win rate against 3 bots, divided by a 70% target and capped at 1. Complex Payments: share of held-out feature tests passed. No official pass rule.
- Score
- 0 of 100
- Nothing to grade, counted as 0. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- q3yngmsffq
- Data release
- 26 Sep 2026
Related runs
| Sol on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 2 hours | 2 h 8 min | 1.07× longer | |
| Middle | 8 hours | 8 h 1 min | Within 5% | |
| Longest (this run) | 30 hours | 6 h 7 min | 4.90× shorter | |
| Other agents, longest request | ||||
| GPT 6 Astra | 30 hours | 30 h 1 min | Within 5% | |
| Claude Fable 5.1 | 30 hours | 8 h 26 min | 3.56× shorter | |
See it on the chart. Transcripts are not published yet.
Read before quoting. This run was stopped by an error, so its time is a lower bound: the agent might have kept going. Details
Data and citation
Upstream: Kinniment et al., 2024 (METR)