Community test: Claude Fable 5.2 predicts protein contact maps from sequence
LeoTZ03 · x · 2026-11-18
A user ran a quick test of the Fable API, asking the model to return protein contact maps directly from amino acid sequences. Shared plots compare three proteins (alpha-helical 6URK, beta-sheet 6L2U, mixed alpha+beta 1YD1) crystal-structure contacts against Claude Fable 5.2's sequence-only output. The model produces plausible contact predictions that partially overlap crystal structures, though notable differences remain — an informal probe of general models' scientific reasoning capabilities.
More from Models
- Raschka: benchmarking new LLMs is like using IQ tests for hiring — rasbt · 2026-11-18
- Open-source Karpo-Decision-31B tops 300-model Decision Index with zero-token, one-forward-pass answers — rohanpaul_ai · 2026-11-18
- GPT-6.2 backlash is real user experience, not astroturf: dev says Astra has quirks but Sol is a solid daily driver — pvncher · 2026-11-18
- LLM protein-folding test on fresh PDB entry lands near-random structures — MoAlQuraishi · 2026-11-18
- Per-task costs span 20x: GPT-6.2 Sol at $2.63 vs Claude Fable 5.2 at $54.25 — haider1 · 2026-11-18
- Every's founder pushes back: we re-tested the model to the wire, OpenAI gave us no heads-up — kieranklaassen · 2026-11-18