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.
More from Models
- Mathematician Levent Alpöge claims proof of Riemann Hypothesis co-discovered with Claude — burny_tech · 2026-11-21
- Google reportedly changing privacy and AI training opt-in controls — blackice193 · 2026-11-21
- Tao announces AI-assisted proofs: Euler/Navier-Stokes blowup and Generalized Riemann Hypothesis — burny_tech · 2026-11-21
- Open-source decision model KarpoDecision31B tops DecisionIndex, 6x faster than Gemini — 量子位 · 2026-11-21
- VideoMemBench shows LLMs forget video chats: best model scores just 45.7 across 25 tested — 机器之心 · 2026-11-21
- 7.5M TTS model holds prosody on long sentences: kale-tts-nano f0 std 2.97 st matches 45.7M sibling — NERDDISCO · 2026-11-21