mark_k: Codex seems generally smarter than ChatGPT even at the same model and effort level
mark_k · x · 2026-10-06
markk observed that Codex seems generally smarter than ChatGPT, even when choosing the same model and effort level — he's not sure why. The observation hints at differences in system prompts, post-processing, or inference configuration between the two products built on the same underlying models.
More from Models
- CoNLL 2023 paper: instruction-tuned GPT models beat children on Theory of Mind tests — dioscuri · 2026-10-06
- User Claims 'GPT-6' Solved His Favorite CTF Fully Autonomously in About an Hour — SIGKITTEN · 2026-10-06
- Mistral Large 4 burns over 2x the output tokens per task vs GPT-6 sol — haider1 · 2026-10-06
- Mistral insider hails Large 4 release as finally making product plans come together — qtnx_ · 2026-10-06
- Reflection AI Claims Beam Is 3-4x More Inference-Efficient Than GLM 5.2 — ChrSzegedy · 2026-10-06
- Dense Wave of Western Model Releases Evokes DeepSeek R1-Era Vibes — serious_mehta · 2026-10-06