Claude 3.5 Sonnet alternatives
The top alternatives to Claude 3.5 Sonnet by Anthropic — comparable LLM models ranked by intelligence index. Claude 3.5 Sonnet itself scores 70.3. Updated automatically from live benchmark data.
- R1 1776Perplexity95.4IndexCompare
- Qwen3.7 MaxAlibaba92.3IndexCompare
- Grok 4.20 0309 v2xAI91.1IndexCompare
- Claude Opus 4.7Anthropic90.9IndexCompare
- Grok 4.3xAI90.1IndexCompare
- DeepSeek V3.2 SpecialeDeepSeek89.9IndexCompare
- DeepSeek-V4-FlashDeepSeek89.4IndexCompare
- GLM 4.7Zhipu AI89IndexCompare
- GPT-5.1OpenAI89IndexCompare
- Qwen3.6 MaxAlibaba88.8IndexCompare
- Grok 4.20 0309xAI88.5IndexCompare
- GPT-5 ProOpenAI88.4IndexCompare
See the full intelligence leaderboard or browse the best models by use case.
New models drop constantly
A free daily email: new models, leaderboard movers, and who leads each category.