Anthropic: Claude Sonnet 5 vs DeepSeek: DeepSeek V4 Pro
Anthropic: Claude Sonnet 5anthropic/claude-sonnet-5VS
DeepSeek: DeepSeek V4 Prodeepseek/deepseek-v4-proAnthropic: Claude Sonnet 5 wins on more metrics (5 of 9), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | Anthropic: Claude Sonnet 5 | DeepSeek: DeepSeek V4 Pro |
|---|---|---|
| Intelligence Index | 53.4✓ | 44.3 |
| Coding Index | 71.5✓ | 59.4 |
| GPQA Diamond | 91%✓ | 89% |
| Design Arena Elo | 1330✓ | 1324 |
| Speed (tokens/sec) | 73✓ | 56 |
| Latency | 2.5s | 549ms✓ |
| Input price /M | $2.00 | $0.435✓ |
| Output price /M | $10.00 | $0.870✓ |
| Context window | 1M | 1.0M✓ |
| Capabilities | ReasoningToolsJSONVision | ReasoningToolsJSON |