Skip to content
PUBLIC QGI R7 / Compare

Compare evidence only when the task is the same.

R7 creates immutable comparison cohorts from published QGI result records. Every member must bind to one exact task manifest, while metrics, uncertainty, resources, failures and validation evidence remain visible instead of being compressed into a universal intelligence score.

Comparison boundary: same-task comparison can show evidence-bearing differences. It does not establish general intelligence, a cross-task winner, QGI level or certification.

Current comparison registry

Integrity: verified

Published cohorts: 0

Universal score: none

Machine-readable comparison protocol →

Rules that make a comparison admissible

Comparison writes are accepted only through the operator CLI publisher; public web routes are read-only.

Every comparison must contain at least two unique, integrity-verified published result IDs.

Every member is bound to the exact result record SHA-256 and evidence packet SHA-256 current at comparison publication.

All members must bind to the same evidence task_manifest_hash; cross-task results cannot be placed in one comparison cohort.

The comparison preserves raw primary metrics, uncertainty, resources, failures and outcome state rather than collapsing them into a universal score.

Metric direction and interpretation must be declared explicitly in metric_contract; unlike metrics are not silently normalised.

Task-specific comparisons may expose evidence-bearing differences, but they do not award a QGI level, universal winner or certification.

Published comparative evaluations

No comparison cohort has been published yet.

R7 does not seed synthetic benchmark winners. Cohorts appear only after at least two real evidence-bearing results exist under the same task manifest.