Company-reported task measures with separate denominators

Two rows keep OpenAI's rounded retrospective task measures separate. Previously unsolved tasks were 198 of 898 total tasks, or 22 percent. OpenAI reports that 93 percent of board-discussed tasks came from that set, using a different denominator.

OpenAI reports that a previously unsolved task set represented 22 percent of all tasks and 93 percent of board-discussed tasks.

Semantic data for Company-reported task measures with separate denominators
RowColumnRecordState
Board discussedBoundaryConditional shareCaution
Board discussedCountNot reportedUnavailable or historical
Board discussedDenominatorBoard-discussed tasksCaution
Board discussedReported share93%Caution
Previously unsolvedBoundaryAll-task shareCaution
Previously unsolvedCount198 tasksCaution
Previously unsolvedDenominator898 total tasksCaution
Previously unsolvedReported share22%Caution
Company-reported task measures with separate denominators Two rows keep OpenAI's rounded retrospective task measures separate. Previously unsolved tasks were 198 of 898 total tasks, or 22 percent. OpenAI reports that 93 percent of board-discussed tasks came from that set, using a different denominator. OpenAI reports that a previously unsolved task set represented 22 percent of all tasks and 93 percent of board-discussed tasks. Boundary Count Denominator Reported shareBoard discussed Conditional share Not reported Board-discussed tasks 93% Previously unsolved All-task share 198 tasks 898 total tasks 22% Cells use text, pattern, and outline in addition to color.
Sources
Retrieved
Units
company-reported task measures
Transformations
  • Do not place 22 percent and 93 percent on a shared quantitative axis, divide the values, calculate uplift, or imply causation.
  • Give each reported measure its own row with an explicit denominator field.
  • Record the unavailable public count behind the board-discussed denominator as not reported.
Uncertainty
OpenAI reports rounded percentages with different denominators. Public counts behind the 93 percent value, uncertainty intervals, and independent replication are unavailable in the reviewed record.
What this figure does not prove
No shared axis is used because the measures have different denominators. The records do not establish causation, uplift, settled intent, a production-wide result, or independent replication.