The Model Index
Models/Anthropic

Claude Fable 5

AnthropicClosed weightsFlagship

Claude Fable 5 is a closed AI model from Anthropic with an index score of 183 (GPT-4 = 100), rank 15 of 217.

183167–199Index score#15 of 217 models
$10/ $50Price per million tokensinput / output · via OpenRouter
1MContext windowtokens it reads at once
9 Jun 2026ReleasedReplaced by Claude Fable 5.1

Where it sitson the frontier

801001201401601802002023202420252026GPT-4 at launch = 100Claude Fable 5

Among the first models to reach this score.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence
GPQA Diamond (Epoch AI)
94%
Humanity's Last Exam
no result
Mathsevidence
FrontierMath (tiers 1-3)
87%
Codingevidence
SWE-bench Verified
no result
Terminal-Bench 4.0
41%
Agentsevidence
APEX-Agents
64%
Professional workevidence
Finance Agent (v2)
56%
Novel problemsevidence
ARC-AGI-2
89%
Long tasksno evidence yet
METR time horizon
no result

Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.

What others sayrank on 12 leaderboards

Best attop three among current models

Where to use itprices checked 18 Nov 2026

Host prices from OpenRouter; going direct can differ.

Facts and sources

Released9 Jun 2026
Announcementanthropic.com ↗
Release entryClaude Fable 5 + Mythos 5 (restricted)
Scored asClaude Fable 5
Output speed–
Hugging Faceclosed weights

Anthropic releasesaround this one

This page as a chartDownload PNG