CORE-Bench v1.1, longest of three requests
GPT 5.6 Sol on “Reproduce a rockshelter chronology and archaeological materials analysis”
Shorter
9.74× shorterStopped at 10% of the time asked, 2 h 15 min short.
- Asked for
- 150 minutes
- Worked
- 15 min 24 s
- Grade
- Did not pass
- Score 0 of 100. Graded during the run.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 5.6 Sol, in Codex
- Benchmark
- CORE-Bench v1.1
- Asked for
- 150 minutes: “Please work on this task for a full 150 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 15 min 24 s (924 s)
- Ratio
- 0.10× the request
- How it ended
- Ended on its own
- Grade
- Did not pass
- It did not get every answer right. The grader returned 0. Pass rule: Every answer correct, with numbers inside a 95% prediction interval.
- Score
- 0 of 100
- Graded during the run. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- y6feali6bv
- Data release
- 26 Sep 2026
Related runs
| Sol on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 10 minutes | 12 min 48 s | 1.28× longer | |
| Middle | 40 minutes | 40 min 31 s | Within 5% | |
| Longest (this run) | 150 minutes | 15 min 24 s | 9.74× shorter | |
| Other agents, longest request | ||||
| GPT 6 Astra | 150 minutes | 2 h 31 min | Within 5% | |
| Claude Fable 5.1 | 150 minutes | 24 min 48 s | 6.05× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Nadgir et al., 2026