Head-to-head
Claude Sonnet 4 (Thinking) vs DeepSeek V3 (Thinking)
Normalized scores are min-maxed per benchmark across all models we track (0–100). Open the interactive compare view to add benchmarks to the radar chart or pull in more models.
Claude Sonnet 4 (Thinking)
AnthropicDeepSeek V3 (Thinking)
DeepSeek| Benchmark | Claude Sonnet 4 (Thinking) | DeepSeek V3 (Thinking) |
|---|---|---|
Chatbot Arena Elo Arena | — | |
LiveCodeBench LiveCB | — | |
Output Speed Speed | — | |
Time to First Token TTFT | — | |
Rolling Contamination-Controlled Average Rolling Avg | ||
Rolling Data Analysis Data Analysis | ||
Humanity's Last Exam HLE | — | |
Aider Polyglot Aider | — | |
Frontier Composite Frontier | — |
Methodology matches the main AI Model Analyzer About page.