Benchmark reports and transcripts
This library will hold complete run packages only after collection, two-pass grading, and adjudication are finished.
No reports published — awaiting run #1
No assistant answers have been collected, graded, or scored. Results will appear only after an approved run completes the published review protocol.
A complete report package will include
- Run manifest and question-set version.
- Full prompts and transcripts.
- Disclosed grading sources and their as-of dates.
- Both independent grading passes and adjudication log.
- Computed scoreboard data and accessible table alternatives.