Claude Fable 5.2
Claude Fable 5.2 is a closed AI model from Anthropic with an index score of 202 (GPT-4 = 100), rank 3 of 217.
202185–218Index score#3 of 217 models
$8.0/ $40Price per million tokensinput / output · via OpenRouter
1MContext windowtokens it reads at once
9 Nov 2026Released9 days ago
Where it sitson the frontier
Among the first models to reach this score.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsevidence
Professional workevidence
Novel problemsevidence
Long tasksno evidence yet
Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.
What others sayrank on 4 leaderboards
The Model Indexthird-party tests, our method#3of 217 · 202
LMArena · WebDevbuilding web apps and front ends#1of 133 · 1826Epoch Capabilities Indexoverall capability from many benchmarks#2of 231 · 173.5LiveBench · Overalloverall, on regularly refreshed questions#1of 38 · 84.9Best attop three among current models
Where to use itprices checked 18 Nov 2026
API providers 4 · per 1M tokens, in / out
Host prices from OpenRouter; going direct can differ.
Facts and sources
Released9 Nov 2026
Announcementanthropic.com ↗
Release entryClaude Fable 5.2
Scored asClaude Fable 5.2
Output speed–
Hugging Faceclosed weights