Cheap Jev verifier nearly matches GPT-6 Astra accuracy but approves more unsupported RAG claims

1. 6:24 AM
   Rohan Paul@rohanpaul_aiX

   Cheap verifier Jev nearly matches GPT-6 Astra on RAG claim checks

   AIA paper tests Jev, a model that returns only a label and probability, against GPT-6 Astra on 495 human-labelled RAG claims. Jev lands within 0.6 points of Astra's accuracy at 187 times lower cost, but approves 23.2% of unsupported claims versus Astra's 14.1%. The authors say teams should measure how often a checker approves unsupported claims, since headline accuracy hides that gap.

   

The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.