Claude Fable 5.2 (Max)

AnthropicProprietary

Claude Fable 5.2 (Max) is a vision-language model from Anthropic. It ranks 10 of 168 on LMArena’s overall vision board with 1313±18 from 1,176 votes. Its best category is Homework (#3 of 119). License: Proprietary.

Key figures

LMArena · Overall1313±18#10 / 168 · Votes 1,176
OCR1327±22#6 / 124 · Votes 790
Diagrams1322±39#16 / 124 · Votes 243
Homework1354±45#3 / 119 · Votes 194
English1315±33#9 / 168 · Votes 365
Developer
Anthropic
License
Proprietary
First seen (our snapshots)
2026-11-20

No data: Captioning, Entity recognition, Creative writing, Humor, Chinese.

Who it suits

  • Overall #10 of 168: top tier, suited to demanding image-understanding work.
  • Strongest category: Homework (#3 of 119).
  • Proprietary; used through Anthropic’s apps or API.

Neighbours on the overall board

#ModelScoreVotesLicenseΔ vs this model
7Claude Opus 4.6 (High) Anthropic131522,067Proprietary+2
8Claude Opus 4.7 (High) Anthropic131422,530Proprietary+1
9Gemini 3.7 Flash (High) Google13146,776Proprietary+1
10Claude Fable 5.2 (Max) Anthropic13131,176Proprietary
11Claude Opus 4.6 Anthropic131226,552Proprietary-1
12Gemini 3.5 Flash (High) Google130815,228Proprietary-5
13Qwen3.8-Max Alibaba130710,833Proprietary-6

Alternatives · More from Anthropic

#ModelScoreVotesLicense
1Claude Fable 5 (High) Anthropic132515,449Proprietary
2Claude Fable 5.1 (Max) Anthropic13227,185Proprietary
3Claude Opus 5.5 (High) Anthropic13225,903Proprietary
4Claude Opus 4.7 Anthropic131724,930Proprietary
5Claude Opus 5 (High) Anthropic131719,229Proprietary

Alternatives · Top open-weight models

#ModelScoreVotesLicense
23GLM-5.3-Flash Z.ai129636,497MIT
35Kimi K2.6 Moonshot AI128216,241Modified MIT
37Gemma 4 31B Google127942,217Apache 2.0
38DeepSeek-V4.1-Flash-20260910 (Max) DeepSeek12784,192MIT
43Qwen3.8-27B Alibaba127110,910Apache 2.0

How to read these scores

  • If two scores differ by less than their ± intervals, the models are statistically close.
  • Each category board is computed independently; do not compare scores across categories.
  • Models with few votes move more; ranks of new entries may change.

FAQ

Where does Claude Fable 5.2 (Max) rank among vision models?

Overall rank 10 (1313); OCR rank 6 (1327); Diagrams rank 16 (1322); Homework rank 3 (1354); English rank 9 (1315) (LMArena, data as of Nov 21, 2026).

How good is Claude Fable 5.2 (Max) at OCR?

Claude Fable 5.2 (Max) ranks 6 of 124 on LMArena’s OCR board with 1327 (790 votes).

Is Claude Fable 5.2 (Max) open-weight?

No. LMArena lists it as Proprietary; it is available through Anthropic’s apps or API.

How far is Claude Fable 5.2 (Max) from #1?

#1 overall is Claude Fable 5 (High) (1325); Claude Fable 5.2 (Max) has 1313, 12 points behind.

Sources

LMArena data published Nov 19, 2026.

Synced here Nov 21, 2026.

Price, context length and release date have no reliable public data here and are not shown; all figures come from snapshots, blanks are –.