Claude 3.5 Sonnet vs DeepSeek V3.2
Head to head on 17 shared benchmarks, with price, context window, and release dates.
Benchmark scores
46evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V3.2 DeepSeek | 74.2% | 94.2% | 47.9% | 1515elo | 66.8 | 22.1% | 84.0% | 24.6% | 65.9% | 64.6% | 48.2% | 70.4% | 86.2% | 86.2% | 38.9% | 70.0% | 68.2% | 74.7% | - | - | - | 0.0% | 13.0% | - | - | 31.3% | 60.7% | 68.0% | - | 50.0% | 85.0% | 77.2% | - | 57.5% | - | 8.0% | - | - | 59.0% | - | 35.6% | 65 | - | 5.1% | - | 90.6% | 55.4% |
| Claude 3.5 Sonnet Anthropic | 51.6% | 3.3% | 53.6% | 1451elo | 58.4 | 2.1% | 55.3% | 4.1% | 63.7% | 65.6% | 69.2% | 56.4% | 38.1% | 77.2% | 36.6% | 63.4% | 70.2% | - | 15.7% | 52.4% | 24.2% | - | - | 28.0% | 96.4 | - | - | - | 0.0% | - | - | - | 77.1% | - | 64.1% | - | 0.0% | 51.3% | - | 25.3% | - | - | 0.98 | - | 62.6% | - | 42.7% |
2 / 2 models
| Attribute | Claude 3.5 Sonnet Anthropic | DeepSeek V3.2 DeepSeek |
|---|---|---|
| Description | Claude Sonnet 3.5 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 Oct 2024 | 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 | MortgageTax64.1% Traveling Salesman0.98 (3 samples) SWE-bench Verified63.4% (SWE-bench) SWE-bench Lite51.3% (SWE-bench) SWE-bench Multimodal25.3% (SWE-bench) | Aider Polyglot Benchmark74.2% (Aider) MathArena57.47% GPQA Diamond84.0% (AA) Humanity's Last Exam (HLE)24.6% (AA) |
FAQ
- Is Claude 3.5 Sonnet or DeepSeek V3.2 better?
- Across the 17 benchmarks both models report on Sophon, DeepSeek V3.2 leads on 13 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Claude 3.5 Sonnet and DeepSeek V3.2 compare on GPQA Diamond?
- Claude 3.5 Sonnet scores 55.3% and DeepSeek V3.2 scores 84.0% on GPQA Diamond.
- Which is cheaper, Claude 3.5 Sonnet or DeepSeek V3.2?
- DeepSeek V3.2 is cheaper at $0.42 per million output tokens against $15.00 for Claude 3.5 Sonnet - about 35.7x.
- When were Claude 3.5 Sonnet and DeepSeek V3.2 released?
- Claude 3.5 Sonnet was released 22 Oct 2024 by Anthropic. DeepSeek V3.2 was released 1 Dec 2025 by DeepSeek.
Other head-to-heads
56DeepSeek V3.2 vs GPT-5.229 shared evalsClaude Sonnet 4.5 vs DeepSeek V3.227 shared evalsClaude Opus 4.5 vs DeepSeek V3.227 shared evalsDeepSeek V3.2 vs GPT-5 Mini26 shared evalsClaude Opus 4.6 vs DeepSeek V3.226 shared evalsDeepSeek V3.2 vs Kimi K2.526 shared evalsDeepSeek V3.2 vs Grok 4.1 Fast26 shared evalsDeepSeek V3.2 vs Gemini 3.1 Pro Preview24 shared evalsDeepSeek V3.2 vs GPT-5.424 shared evalsDeepSeek V3.2 vs GLM 5.124 shared evalsDeepSeek V3.2 vs GPT-5.523 shared evalsClaude Sonnet 4.6 vs DeepSeek V3.223 shared evalsClaude Opus 4.7 vs DeepSeek V3.223 shared evalsDeepSeek V3.2 vs gpt-oss-120b23 shared evalsDeepSeek V3.2 vs GPT-5 Nano22 shared evalsClaude Opus 4.8 vs DeepSeek V3.222 shared evalsClaude 3.5 Sonnet vs GPT-4o22 shared evalsDeepSeek V3.2 vs GLM 4.722 shared evalsClaude 4 Sonnet vs DeepSeek V3.221 shared evalsClaude 3.5 Sonnet vs Claude 4 Sonnet21 shared evalsDeepSeek V3.2 vs Gemini 2.5 Pro21 shared evalsClaude 3.5 Sonnet vs Gemini 2.5 Pro21 shared evalsClaude Fable 5 vs DeepSeek V3.220 shared evalsDeepSeek V3.2 vs Qwen3.6 Plus20 shared evalsClaude 3.5 Sonnet vs Claude Sonnet 4.519 shared evalsClaude 3.5 Sonnet vs GPT-5 Mini19 shared evalsDeepSeek V3.2 vs GPT-519 shared evalsClaude 3.5 Sonnet vs GPT-4o-mini19 shared evalsClaude 3.5 Sonnet vs GPT-4.118 shared evalsDeepSeek V3.2 vs GPT-4o18 shared evalsClaude 3.5 Sonnet vs GPT-4.1 Mini17 shared evalsClaude 3.5 Sonnet vs GPT-517 shared evalsClaude 3.5 Sonnet vs GPT-5 Nano17 shared evalsClaude 3.5 Sonnet vs GPT-5.217 shared evalsClaude 3.5 Sonnet vs Claude Opus 4.517 shared evalsClaude 3.5 Sonnet vs GPT-4.1 Nano16 shared evalsClaude 3.5 Sonnet vs gpt-oss-120b16 shared evalsDeepSeek V3.2 vs GPT-4.1 Mini15 shared evalsClaude 3.5 Sonnet vs Kimi K2.515 shared evalsDeepSeek V3.2 vs GPT-4.115 shared evalsDeepSeek V3.2 vs GPT-4o-mini15 shared evalsDeepSeek V3.2 vs GPT-4.1 Nano15 shared evalsClaude 3.5 Sonnet vs Grok 4.1 Fast15 shared evalsClaude 3.5 Sonnet vs GLM 4.715 shared evalsClaude 3.5 Sonnet vs GPT-5.514 shared evalsClaude 3.5 Sonnet vs Claude Opus 4.614 shared evalsClaude 3.5 Sonnet vs Gemini 3.1 Pro Preview13 shared evalsClaude 3.5 Sonnet vs Claude Opus 4.813 shared evalsClaude 3.5 Sonnet vs GPT-5.413 shared evalsClaude 3.5 Sonnet vs GLM 5.113 shared evalsClaude 3.5 Sonnet vs Claude Sonnet 4.613 shared evalsClaude 3.5 Sonnet vs Claude Opus 4.713 shared evalsClaude 3.5 Sonnet vs Claude Fable 512 shared evalsClaude 3.5 Sonnet vs Qwen3.6 Plus11 shared evalsDeepSeek V3.2 vs GPT-6 Astra9 shared evalsClaude 3.5 Sonnet vs GPT-6 Astra6 shared evals
Comparing something else? Build your own side-by-side.