Claude Sonnet 4 (Thinking 32K, 20250514)
AnthropicProprietary
Claude Sonnet 4 (Thinking 32K, 20250514) is a vision-language model from Anthropic. It ranks 100 of 167 on LMArena’s overall vision board with 1191±17 from 1,144 votes. Its best category is OCR (#96 of 123). License: Proprietary.
Key figures
- Developer
- Anthropic
- License
- Proprietary
- First seen (our snapshots)
- 2026-10-26
No data: Homework, Captioning, Entity recognition, Creative writing, Humor, Chinese.
Who it suits
- Overall #100 of 167: lower half; consider it mainly for cost or deployment reasons.
- Strongest category: OCR (#96 of 123).
- Proprietary; used through Anthropic’s apps or API.
Neighbours on the overall board
| # | Model | Score | Votes | License | Δ vs this model |
|---|---|---|---|---|---|
| 97 |  GPT-4.5 Preview (2025-02-27) OpenAI | 1195 | 2,925 | Proprietary | +4 |
| 98 | o4-mini (2025-04-16) OpenAI | 1194 | 41,316 | Proprietary | +3 |
| 99 | Claude Opus 4 (Thinking 16K, 20250514) Anthropic | 1192 | 1,290 | Proprietary | +1 |
| 100 | Claude Sonnet 4 (Thinking 32K, 20250514) Anthropic | 1191 | 1,144 | Proprietary | |
| 101 |  Gemini 2.5 Flash-Lite Preview (Thinking, 06-17) Google | 1187 | 35,914 | Proprietary | -4 |
| 102 | SStep-1o Turbo (202506) StepFun | 1186 | 1,895 | Proprietary | -5 |
| 103 | GPT-4.1 mini (2025-04-14) OpenAI | 1181 | 40,201 | Proprietary | -10 |
Alternatives · More from Anthropic
| # | Model | Score | Votes | License |
|---|---|---|---|---|
| 1 | Claude Fable 5 (High) Anthropic | 1325 | 14,714 | Proprietary |
| 2 | Claude Opus 5.5 (High) Anthropic | 1321 | 3,035 | Proprietary |
| 3 | Claude Opus 5 (High) Anthropic | 1320 | 17,743 | Proprietary |
| 4 | Claude Fable 5.1 (Max) Anthropic | 1319 | 5,026 | Proprietary |
| 5 | Claude Opus 4.7 Anthropic | 1317 | 23,139 | Proprietary |
Alternatives · Top open-weight models
| # | Model | Score | Votes | License |
|---|---|---|---|---|
| 24 |  GLM-5.3-Flash Z.ai | 1294 | 16,254 | MIT |
| 34 |  Kimi K2.6 Moonshot AI | 1282 | 16,368 | Modified MIT |
| 38 |  DeepSeek-V4.1-Flash-20260910 (Max) DeepSeek | 1278 | 4,100 | MIT |
| 39 | Gemma 4 31B Google | 1276 | 40,219 | Apache 2.0 |
| 44 |  Qwen3.8-27B Alibaba | 1269 | 7,614 | Apache 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 Sonnet 4 (Thinking 32K, 20250514) rank among vision models?
Overall rank 100 (1191); OCR rank 96 (1197); Diagrams rank 96 (1200); English rank 106 (1186) (LMArena, data as of Oct 26, 2026).
How good is Claude Sonnet 4 (Thinking 32K, 20250514) at OCR?
Claude Sonnet 4 (Thinking 32K, 20250514) ranks 96 of 123 on LMArena’s OCR board with 1197 (725 votes).
Is Claude Sonnet 4 (Thinking 32K, 20250514) open-weight?
No. LMArena lists it as Proprietary; it is available through Anthropic’s apps or API.
How far is Claude Sonnet 4 (Thinking 32K, 20250514) from #1?
#1 overall is Claude Fable 5 (High) (1325); Claude Sonnet 4 (Thinking 32K, 20250514) has 1191, 134 points behind.
Sources
LMArena data published Oct 19, 2026.
Synced here Oct 26, 2026.
Price, context length and release date have no reliable public data here and are not shown; all figures come from snapshots, blanks are –.