Claude 3.5 Sonnet vs Claude 4 Sonnet
Head to head on 21 shared benchmarks, with price, context window, and release dates.
Benchmark scores
49evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude 4 Sonnet Anthropic | 77.3% | 74.3% | 54.7% | 19.8% | 1483elo | 58.4 | 77.7% | 10.7% | 64.8% | 77.5% | 44.3% | 72.9% | 65.5% | 99.1% | 84.2% | 62.5% | 40.0% | 58.3% | 35.6% | 74.6% | 69.6% | - | - | - | 22.9% | 47.8% | - | 67.5% | - | 54.7% | - | 54.6% | 70.5% | 69.0% | 33.9% | 72.4% | 86.7% | 43.9% | - | 6.18 | 6.18 | 35.0% | 31.1% | - | 0.59 | 84.0% | 84.0% | - | 64.6% | 59.6% |
| Claude 3.5 Sonnet Anthropic | 15.7% | 3.3% | 53.6% | 28.0% | 1451elo | 58.4 | 55.3% | 4.1% | 63.7% | 65.6% | 69.2% | 56.4% | 38.1% | 77.1% | 77.2% | 64.1% | 36.6% | 51.3% | 25.3% | 63.4% | 70.2% | 51.6% | 52.4% | 24.2% | - | - | 2.1% | - | 96.4 | - | 0.0% | - | - | - | - | - | - | - | 0.0% | - | - | - | - | 0.98 | - | - | - | 62.6% | - | 42.7% |
2 / 2 models
| Attribute | Claude 3.5 Sonnet Anthropic | Claude 4 Sonnet Anthropic |
|---|---|---|
| Description | Claude Sonnet 3.5 is an AI model from Anthropic. | Claude 4 Sonnet is an AI model from Anthropic. |
| Family | Claude | Claude |
| Params | - | - |
| Open weights | closed | closed |
| License | proprietary | proprietary |
| Released | 22 Oct 2024 | 22 May 2025 |
| Context | 200,000 | 200,000 |
| Input $/1M | $3.00 | - |
| Output $/1M | $15.00 | - |
| Cache read $/1M | - | - |
| Cache write $/1M | - | - |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | text, image | text, image |
| Providers | - | - |
| Publisher | Anthropic | Anthropic |
| 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) |
FAQ
- Is Claude 3.5 Sonnet or Claude 4 Sonnet better?
- Across the 21 benchmarks both models report on Sophon, Claude 4 Sonnet leads on 16 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Claude 3.5 Sonnet and Claude 4 Sonnet compare on GPQA Diamond?
- Claude 3.5 Sonnet scores 55.3% and Claude 4 Sonnet scores 77.7% on GPQA Diamond.
- When were Claude 3.5 Sonnet and Claude 4 Sonnet released?
- Claude 3.5 Sonnet was released 22 Oct 2024 by Anthropic. Claude 4 Sonnet was released 22 May 2025 by Anthropic.
Other head-to-heads
56Claude 4 Sonnet vs GPT-5 Mini29 shared evalsClaude 4 Sonnet vs Claude Sonnet 4.528 shared evalsClaude 4 Sonnet vs Claude Opus 4.526 shared evalsClaude 4 Sonnet vs GPT-525 shared evalsClaude 4 Sonnet vs GPT-5 Nano25 shared evalsClaude 4 Sonnet vs GPT-5.225 shared evalsClaude 4 Sonnet vs Gemini 2.5 Pro25 shared evalsClaude 4 Sonnet vs Kimi K2.524 shared evalsClaude 4 Sonnet vs Grok 4.1 Fast24 shared evalsClaude 4 Sonnet vs GPT-5.523 shared evalsClaude 4 Sonnet vs Gemini 3.1 Pro Preview23 shared evalsClaude 4 Sonnet vs Claude Opus 4.822 shared evalsClaude 4 Sonnet vs Claude Fable 522 shared evalsClaude 4 Sonnet vs GPT-5.422 shared evalsClaude 4 Sonnet vs Claude Opus 4.622 shared evalsClaude 4 Sonnet vs GLM 4.722 shared evalsClaude 3.5 Sonnet vs GPT-4o22 shared evalsClaude 4 Sonnet vs Claude Opus 4.721 shared evalsClaude 4 Sonnet vs DeepSeek V3.221 shared evalsClaude 4 Sonnet vs gpt-oss-120b21 shared evalsClaude 3.5 Sonnet vs Gemini 2.5 Pro21 shared evalsClaude 4 Sonnet vs GLM 5.120 shared evalsClaude 4 Sonnet vs Claude Sonnet 4.620 shared evalsClaude 4 Sonnet vs GPT-4o20 shared evalsClaude 4 Sonnet vs GPT-4.1 Mini19 shared evalsClaude 3.5 Sonnet vs Claude Sonnet 4.519 shared evalsClaude 3.5 Sonnet vs GPT-5 Mini19 shared evalsClaude 4 Sonnet vs GPT-4.119 shared evalsClaude 4 Sonnet vs Qwen3.6 Plus19 shared evalsClaude 3.5 Sonnet vs GPT-4o-mini19 shared evalsClaude 4 Sonnet vs GPT-4o-mini18 shared evalsClaude 3.5 Sonnet vs GPT-4.118 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 DeepSeek V3.217 shared evalsClaude 4 Sonnet vs GPT-4.1 Nano16 shared evalsClaude 3.5 Sonnet vs GPT-4.1 Nano16 shared evalsClaude 3.5 Sonnet vs gpt-oss-120b16 shared evalsClaude 3.5 Sonnet vs Kimi K2.515 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 evalsClaude 4 Sonnet vs GPT-6 Astra8 shared evalsClaude 3.5 Sonnet vs GPT-6 Astra6 shared evals
Comparing something else? Build your own side-by-side.