Claude Sonnet 4.6 vs DeepSeek V3.2
Head to head on 23 shared benchmarks, with price, context window, and release dates.
Benchmark scores
45evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 4.6 Anthropic | 65.3% | 78.0% | 1805elo | 79.9 | 32.4% | 79.7% | 11.2% | 42.4% | 92.2% | 78.4% | 80.0% | 76.1% | 63.9% | 77.7% | 86.5% | 86.4% | 45.0% | 44.1% | 77.1% | 42.4% | 76.3 | 51.5% | 78.9% | - | 87.1% | - | - | 47.2% | 47.6% | - | 1.35 | 1207elo | 51.0% | - | - | - | - | 89.3 | 67.7% | 72.1% | 46.6% | - | - | 50.6% | 60.6% | 62.8% |
| DeepSeek V3.2 DeepSeek | 47.9% | 16.0% | 1511elo | 66.8 | 22.1% | 75.1% | 11.2% | 49.0% | 68.0% | 65.9% | 64.6% | 50.0% | 48.2% | 70.4% | 85.0% | 77.2% | 8.0% | 38.7% | 68.2% | 32.6% | 65 | 5.1% | 78.9% | 74.7% | - | 74.2% | 59.0% | - | - | 0.0% | - | - | - | 31.3% | 59.3% | 57.5% | 83.7% | - | - | - | - | 59.0% | 70.0% | - | - | 51.7% |
2 / 2 models
| Attribute | Claude Sonnet 4.6 Anthropic | DeepSeek V3.2 DeepSeek |
|---|---|---|
| Description | Claude Sonnet 4.6 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 | 17 Feb 2026 | 1 Dec 2025 |
| Context | 1,000,000 | 163,840 |
| Input $/1M | $3.00 | $0.28 |
| Output $/1M | $15.00 | $0.42 |
| Cache read $/1M | $0.300 | $0.130 |
| Cache write $/1M | $3.750 | - |
| Speed | 45 tok/s | 0 tok/s |
| Latency | 1.12 s | 0.00 s |
| Modalities | text, image, file | text |
| Providers | - | - |
| Publisher | Anthropic | DeepSeek |
| Reported scores | GPQA Diamond79.7% (AA) Humanity's Last Exam (HLE)11.2% (AA) IFBench42.4% (AA) SciCode44.1% (AA) τ²-bench (Tau²-bench)78.9% (AA) | Aider Polyglot Benchmark74.2% (Aider) MathArena57.47% GPQA Diamond75.1% (AA) Humanity's Last Exam (HLE)11.2% (AA) |
FAQ
- Is Claude Sonnet 4.6 or DeepSeek V3.2 better?
- Across the 23 benchmarks both models report on Sophon, Claude Sonnet 4.6 leads on 20 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Claude Sonnet 4.6 and DeepSeek V3.2 compare on GPQA Diamond?
- Claude Sonnet 4.6 scores 79.7% and DeepSeek V3.2 scores 75.1% on GPQA Diamond.
- Which is cheaper, Claude Sonnet 4.6 or DeepSeek V3.2?
- DeepSeek V3.2 is cheaper at $0.42 per million output tokens against $15.00 for Claude Sonnet 4.6 - about 35.7x.
- When were Claude Sonnet 4.6 and DeepSeek V3.2 released?
- Claude Sonnet 4.6 was released 17 Feb 2026 by Anthropic. DeepSeek V3.2 was released 1 Dec 2025 by DeepSeek.
Comparing something else? Build your own side-by-side.