# Claude Fable 5 review: 9.8/10

URL: https://ongchummo.vn/en/review-ai-tool/claude-fable-5

Category: Frontier LLM · Pricing: Paid
Tool website: https://www.anthropic.com/claude

## Verdict

The version geared toward writing and broad knowledge, ranked first on Arena text and the hardest knowledge benchmarks.

## Scores by task (out of 10)

- Video: 8.4
- Image: 9.2
- 3D: 8
- Chat: 10
- Code: 9.4
- Web: 9.6

## Strengths

- #1 on Arena text at 1508.6 and Humanity's Last Exam at 53.3%
- #1 on A-Omniscience at 40, the broadest knowledge right now
- 1M context

## Weaknesses

- $10/$50, the most expensive in this table
- Not as strong as Opus 5 at agentic coding
- Overkill for short, repetitive tasks

## Full review

### Ranking source
Updated August 9, 2026 from the Artificial Analysis Intelligence Index (v4.1 scale), cross-checked against each provider's release notes and official pages. Scores on the v4.1 scale can't be compared directly with earlier rankings.

### When to use it
Use it when you need substantial long-form writing, multi-source research, or answers to in-depth knowledge questions.

### Notes
AA Intelligence Index: 62 (with fallback); context 1M; GA June 9, 2026; price $10/$50. If your main work is code and agents, Opus 5 is the better fit, at a lower price.
