Claude Sonnet 4.6 vs DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 edges ahead on overall intelligence (RunFree 72.4 vs 66.2). Here's how they stack up on benchmarks, price and specs.
Claude Sonnet 4.6
Anthropic
DeepSeek V4 Pro 0423
DeepSeek
Shared benchmarks (4)
Loading chart…
| Claude Sonnet 4.6 | DeepSeek V4 Pro 0423 | |
|---|---|---|
| RunFree Score | 66.2 | 72.4 |
| Blended price / 1M | $6.00 | $1.19 |
| Input / 1M | $3.00 | $0.95 |
| Output / 1M | $15.00 | $1.91 |
| Context window | 1M | 1.0M |
| Max output | 128K | 384K |
| Reasoning model | Yes | Yes |
| GPQA Diamond | 89.9% | 90.1% |
| Humanity's Last Exam | 33.2% | 37.7% |
| SWE-Bench Verified | 79.6% | 80.6% |
| Terminal-Bench | 59.1% | 67.9% |
| Wins | 0 | 10 |
A blank means the metric is tied or one model has no verified data. Prices are blended 3:1 input:output.
Compare more: Claude Sonnet 4.6 card · DeepSeek V4 Pro 0423 card · full leaderboard