All Comparisons
Claude Sonnet 4 vs DeepSeek-R1
Claude Sonnet 4
Anthropic 🇺🇸
68.9
#73—
high$3.00/M in · $15.00/M out
200K context
DeepSeek-R1
DeepSeek 🇨🇳
Most Affordable
Claude Sonnet 4
$3.00/M input
Largest Context
Claude Sonnet 4
200K tokens
Best Benchmark Score
Claude Sonnet 4
68.9/100
Model Specifications
| Spec | Claude Sonnet 4 | DeepSeek-R1 |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Release Date | May 2025 | Jan 2025 |
| Knowledge Cutoff | Mar 2025 | — |
| Parameters | unknown | 671000000000B |
| Context Window | 200K | — |
| Max Output | — | — |
| Open Source | No | Yes |
| License | proprietary | mit |
| Tokenizer | — | — |
| Modality | — | — |
| Reasoning Model |
Pricing Comparison
| Price (per 1M tokens) | Claude Sonnet 4 | DeepSeek-R1 |
|---|---|---|
| Input | $3.00 | — |
| Output | $15.00 | — |
API Provider Pricing
Capabilities
| Feature | Claude Sonnet 4 | DeepSeek-R1 |
|---|---|---|
| Text Input | ||
| Image Input (Vision) | ||
| Audio Input | ||
| Video Input |
Category Comparison
Benchmark-by-Benchmark
general
| Benchmark | Claude Sonnet 4 | DeepSeek-R1 |
|---|---|---|
| MMLU-Pro | 80.2 | — |
| IFEval | 90.1 | — |
| Chatbot Arena Elo | 1310 | — |
coding
| Benchmark | Claude Sonnet 4 | DeepSeek-R1 |
|---|---|---|
| HumanEval |
Category Winners
coding
54.5
math
66.8
reasoning
71.6
general
90.0
multimodal
63.7