Claude 3.7 Sonnet (20250219)

AnthropicProprietary

Claude 3.7 Sonnet (20250219) is a vision-language model from Anthropic. It ranks 120 of 167 on LMArena’s overall vision board with 1151±9 from 4,516 votes. Its best category is Homework (#98 of 118). License: Proprietary.

Key figures

LMArena · Overall1151±9#120 / 167 · Votes 4,516
OCR1157±19#111 / 123 · Votes 879
Diagrams1153±32#111 / 123 · Votes 290
Homework1207±37#98 / 118 · Votes 216
English1141±13#127 / 167 · Votes 2,155
Chinese1174±47#102 / 135 · Votes 163
Developer
Anthropic
License
Proprietary
First seen (our snapshots)
2026-10-26

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

Who it suits

  • Overall #120 of 167: lower half; consider it mainly for cost or deployment reasons.
  • Strongest category: Homework (#98 of 118).
  • Proprietary; used through Anthropic’s apps or API.

Neighbours on the overall board

#ModelScoreVotesLicenseΔ vs this model
117Mistral Medium 3 (2505) Mistral115710,773Proprietary+6
118GLM-4.5V Z.ai11543,233MIT+3
119Qwen2.5-VL-32B-Instruct Alibaba11521,490Apache 2.0+1
120Claude 3.7 Sonnet (20250219) Anthropic11514,516Proprietary
121Mistral Small 3.2 (2506) Mistral114210,825Apache 2.0-9
122Llama 4 Maverick 17B 128E Instruct Meta11426,912Llama 4-9
123Gemini 1.5 Flash (002) Google11417,241Proprietary-10

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
4Claude Opus 4.7 Anthropic131923,777Proprietary
5Claude Opus 5 (High) Anthropic131719,345Proprietary

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 3.7 Sonnet (20250219) rank among vision models?

Overall rank 120 (1151); OCR rank 111 (1157); Diagrams rank 111 (1153); Homework rank 98 (1207); English rank 127 (1141); Chinese rank 102 (1174) (LMArena, data as of Nov 14, 2026).

How good is Claude 3.7 Sonnet (20250219) at OCR?

Claude 3.7 Sonnet (20250219) ranks 111 of 123 on LMArena’s OCR board with 1157 (879 votes).

Is Claude 3.7 Sonnet (20250219) better with Chinese or English prompts?

Chinese board: #102 of 135 (1174); English board: #127 of 167 (1141). The boards are computed separately, so compare ranks rather than scores.

Is Claude 3.7 Sonnet (20250219) open-weight?

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

How far is Claude 3.7 Sonnet (20250219) from #1?

#1 overall is Claude Fable 5 (High) (1326); Claude 3.7 Sonnet (20250219) has 1151, 175 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 –.