Anthropic: Claude Opus 4.8 vs DeepSeek: DeepSeek V4 Pro
Anthropic: Claude Opus 4.8anthropic/claude-opus-4.8VS
DeepSeek: DeepSeek V4 Prodeepseek/deepseek-v4-proDeepSeek: DeepSeek V4 Pro wins on more metrics (5 of 9), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | Anthropic: Claude Opus 4.8 | DeepSeek: DeepSeek V4 Pro |
|---|---|---|
| Intelligence Index | 55.7✓ | 44.3 |
| Coding Index | 74.3✓ | 59.4 |
| GPQA Diamond | 92%✓ | 89% |
| Design Arena Elo | 1288 | 1324✓ |
| Speed (tokens/sec) | 72✓ | 56 |
| Latency | 1.8s | 549ms✓ |
| Input price /M | $5.00 | $0.435✓ |
| Output price /M | $25.00 | $0.870✓ |
| Context window | 1M | 1.0M✓ |
| Capabilities | ReasoningToolsJSONVision | ReasoningToolsJSON |