6-round eval shows GPT-6.2-sol matching only 11/23 judge outcomes vs 6.1's 21/23

0xkarasy · x · 2026-11-21

0xkarasy shared an eval table arguing OpenAI "clearly dropped the ball" on the gpt-6.2 models: in an LLM-judge agreement test over 23 cases, gpt-6.1-sol matched the author's outcomes on 21 of 23, while the newer gpt-6.2-sol matched only 11 of 23 — after six rounds of evals, a substantial regression for the new model. A third-party quality critique of OpenAI's latest release.

Original post →

More from Models

Models channel →