Claude Opus 4.7

AnthropicProprietary

Claude Opus 4.7 is a vision-language model from Anthropic. It ranks 4 of 167 on LMArena’s overall vision board with 1319±7 from 23,777 votes. Its best category is OCR (#5 of 123). License: Proprietary.

Key figures

LMArena · Overall1319±7#4 / 167 · Votes 23,777
OCR1328±7#5 / 123 · Votes 17,187
Diagrams1335±9#9 / 123 · Votes 6,544
Homework1335±11#12 / 118 · Votes 3,258
Entity recognition1225±43#32 / 52 · Votes 155
Creative writing1324±16#7 / 106 · Votes 1,455
Humor1310±20#12 / 102 · Votes 912
English1322±9#3 / 167 · Votes 9,986
Chinese1372±17#10 / 135 · Votes 1,529
Developer
Anthropic
License
Proprietary
First seen (our snapshots)
2026-10-26

No data: Captioning.

Who it suits

  • Overall #4 of 167: top tier, suited to demanding image-understanding work.
  • Strongest category: OCR (#5 of 123).
  • Proprietary; used through Anthropic’s apps or API.

Neighbours on the overall board

#ModelScoreVotesLicenseΔ vs this model
1Claude Fable 5 (High) Anthropic132615,536Proprietary+7
2Claude Opus 5.5 (High) Anthropic13244,789Proprietary+5
3Claude Fable 5.1 (Max) Anthropic13226,296Proprietary+3
4Claude Opus 4.7 Anthropic131923,777Proprietary
5Claude Opus 5 (High) Anthropic131719,345Proprietary-2
6Gemini 3.8 Flash (High) Google13177,624Proprietary-2
7Claude Opus 4.6 (High) Anthropic131622,116Proprietary-3

Alternatives · More from Anthropic

#ModelScoreVotesLicense
1Claude Fable 5 (High) Anthropic132615,536Proprietary
2Claude Opus 5.5 (High) Anthropic13244,789Proprietary
3Claude Fable 5.1 (Max) Anthropic13226,296Proprietary
5Claude Opus 5 (High) Anthropic131719,345Proprietary
7Claude Opus 4.6 (High) Anthropic131622,116Proprietary

Alternatives · Top open-weight models

#ModelScoreVotesLicense
24GLM-5.3-Flash Z.ai129531,530MIT
34Kimi K2.6 Moonshot AI128216,265Modified MIT
36Gemma 4 31B Google127941,787Apache 2.0
37DeepSeek-V4.1-Flash-20260910 (Max) DeepSeek12794,247MIT
42Qwen3.8-27B Alibaba12709,632Apache 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 Opus 4.7 rank among vision models?

Overall rank 4 (1319); OCR rank 5 (1328); Diagrams rank 9 (1335); Homework rank 12 (1335); Entity recognition rank 32 (1225); Creative writing rank 7 (1324); Humor rank 12 (1310); English rank 3 (1322); Chinese rank 10 (1372) (LMArena, data as of Nov 14, 2026).

How good is Claude Opus 4.7 at OCR?

Claude Opus 4.7 ranks 5 of 123 on LMArena’s OCR board with 1328 (17,187 votes).

Is Claude Opus 4.7 better with Chinese or English prompts?

Chinese board: #10 of 135 (1372); English board: #3 of 167 (1322). The boards are computed separately, so compare ranks rather than scores.

Is Claude Opus 4.7 open-weight?

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

How far is Claude Opus 4.7 from #1?

#1 overall is Claude Fable 5 (High) (1326); Claude Opus 4.7 has 1319, 7 points behind.

Sources

LMArena data published Nov 9, 2026.

Synced here Nov 14, 2026.

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