The groups of this benchmark
One row per prediction file, and one run per database it names, because a connection here is one file. The numbers are the sums of that group's runs, which they can be because no question is in two of them. Every benchmark is indexed a level up.
| group | runs | audited | compared | GOLD-ONLY | probes fired | credited by BIRD and NOT_EQUAL | ERROR |
|---|---|---|---|---|---|---|---|
| dev-20251106 | 11 | 1,534 | 0 | 1,531 | 47 | 0 | 3 |