Claude 4 Sonnet vs DeepSeek V3.2
Head to head on 21 shared benchmarks, with price, context window, and release dates.
Benchmark scores
52evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude 4 Sonnet Anthropic | 38.0% | 54.7% | 1480elo | 58.4 | 68.3% | 4.3% | 45.4% | 64.8% | 77.5% | 54.6% | 44.3% | 72.9% | 70.5% | 69.0% | 44.9% | 83.7% | 37.3% | 74.6% | 69.6% | 27.3% | 52.3% | - | - | 40.7% | 22.9% | 47.8% | - | - | 19.8% | - | 67.5% | - | - | 93.4% | - | 33.9% | 72.4% | 86.7% | 62.5% | 43.9% | - | 6.18 | 6.18 | 35.0% | 58.3% | - | 35.6% | - | 0.59 | - | 84.0% | 84.0% | 55.5% |
| DeepSeek V3.2 DeepSeek | 59.0% | 47.9% | 1511elo | 66.8 | 75.1% | 11.2% | 49.0% | 65.9% | 64.6% | 50.0% | 48.2% | 70.4% | 85.0% | 77.2% | 59.3% | 83.7% | 38.7% | 70.0% | 68.2% | 32.6% | 78.9% | 74.7% | 74.2% | - | - | - | 0.0% | 16.0% | - | 22.1% | - | 31.3% | 68.0% | - | 57.5% | - | - | - | - | - | 8.0% | - | - | - | - | 59.0% | - | 65 | - | 5.1% | - | - | 51.7% |
2 / 2 models
| Attribute | Claude 4 Sonnet Anthropic | DeepSeek V3.2 DeepSeek |
|---|---|---|
| Description | Claude 4 Sonnet is an AI model from Anthropic. | DeepSeek V3.2 is an AI model from DeepSeek, released with open weights. |
| Family | Claude | Deepseek |
| Params | - | - |
| Open weights | closed | open |
| License | proprietary | mit |
| Released | 22 May 2025 | 1 Dec 2025 |
| Context | 200,000 | 163,840 |
| Input $/1M | $3.00 | $0.28 |
| Output $/1M | $15.00 | $0.42 |
| Cache read $/1M | - | $0.130 |
| Cache write $/1M | - | - |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | text, image | text |
| Providers | - | - |
| Publisher | Anthropic | DeepSeek |
| Reported scores | Aider Polyglot Benchmark74.2% (Aider) MathArena57.47% GPQA Diamond75.1% (AA) Humanity's Last Exam (HLE)11.2% (AA) |
FAQ
- Is Claude 4 Sonnet or DeepSeek V3.2 better?
- Across the 21 benchmarks both models report on Sophon, DeepSeek V3.2 leads on 14 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Claude 4 Sonnet and DeepSeek V3.2 compare on GPQA Diamond?
- Claude 4 Sonnet scores 68.3% and DeepSeek V3.2 scores 75.1% on GPQA Diamond.
- Which is cheaper, Claude 4 Sonnet or DeepSeek V3.2?
- DeepSeek V3.2 is cheaper at $0.42 per million output tokens against $15.00 for Claude 4 Sonnet - about 35.7x.
- When were Claude 4 Sonnet and DeepSeek V3.2 released?
- Claude 4 Sonnet was released 22 May 2025 by Anthropic. DeepSeek V3.2 was released 1 Dec 2025 by DeepSeek.
Comparing something else? Build your own side-by-side.