Head-to-head test of three flagship models: Fable 5.2 still leads, but not a clean sweep
petergyang · x · 2026-11-18
A new video pits three flagship models against each other across video, games, design, writing, and how well they hold up when pushed back — and Fable 5.2 does NOT win on everything.
Key takeaways:
- Astra (OpenAI): Feels "lazy" — did an incomplete analysis of YouTube stats and wrote an off-topic essay. The author argues OpenAI models have lost the drive of the 5.6 era, though its design taste has improved.
- Gemini 4 Carbon: Surprisingly strong at writing, works harder and feels smarter than Astra, but is slow and weak at design/3D, stuffing the UX with too much info.
- Fable 5.2: Still the best overall, keeps surprising with its creativity.
More from Models
- Asking Gemini 10,701 questions: Google Search rewrites ~45% of brand picks — dejanseo · 2026-11-18
- Cursor's CursorBench 4.0: Gemini 4 Carbon tops at 60.4%, DeepSeek under $1 per task — mattyp · 2026-11-18
- Salesforce's SOV-Transcribe-1 ASR model trends on Hugging Face — salesforce-sovereign-intelligence · 2026-11-18
- Test: Google's AI Mode default Gemini 4 Hydrogen knows almost nothing about brands without search — dejanseo · 2026-11-18
- OpenAI explains the 6.2 influencer/community vibe gap: demo videos used pre-release models — i_dg23 · 2026-11-18
- Ruff author Charlie Marsh: GPT-6.2 was an enormous step-up for my work — charliermarsh · 2026-11-18