Claude 3.7 Sonnet: pricing, context window and benchmarks
Claude 3.7 Sonnet is a multimodal model from Anthropic. It offers a 200,000-token context window, costs $14.91 per million input tokens and $74.27 per million output tokens, and averages 81.6 across the index's benchmark suite.
Pricing
Claude 3.7 Sonnet costs $14.91 per million input tokens and $74.27 per million output tokens. A blended 3:1 input-to-output mix works out to about $29.75 per million tokens. Cached input is listed at $1.70 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $14.91 | per 1M tokens |
| Output | $74.27 | per 1M tokens |
| Cached input | $1.70 | per 1M tokens |
| Blended 3:1 | $29.75 | estimate per 1M tokens |
| 1M in + 1M out | $89.18 | estimate |
Benchmarks
Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 83.5 | 93 | 85th | |
| GPQA Diamond | 80.2 | 53 | 91th | |
| SWE-bench Verified | 70.1 | 107 | 82th | |
| HumanEval | 85.7 | 103 | 83th | |
| MATH-500 | 88.9 | 60 | 90th | |
| AIME 2025 | 81.2 | 70 | 88th | |
| LiveCodeBench | 75.0 | 95 | 84th | |
| IFEval | 88.5 | 94 | 84th | |
| TruthfulQA | 81.7 | 133 | 78th | |
| HellaSwag | 87.6 | 156 | 74th | |
| MMMU | 75.5 | 149 | 75th | |
| Arena Elo | 1451.9 | 68 | 89th |
What Claude 3.7 Sonnet is good for
Claude 3.7 Sonnet is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $14.91 per million input tokens, it sits in the mid-range of the index, and the 200,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 200,000-token context window for long documents and agent traces.
- Accepts more than text, including image input where the provider supports it.
- Coding benchmarks are a relative strength within its tier.
Trade-offs
- Proprietary licence: you cannot download the weights or self-host the model.
- Premium input pricing at $14.91 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Llama 4 Maverick Instruct | Meta AI | 200000 | $5.33 | 81.7 |
| Mistral Large 3 | Mistral AI | 128000 | $5.41 | 81.7 |
| Claude 3.7 Sonnet | Anthropic | 200000 | $14.91 | 81.6 |
| Doubao 1.5 Pro Reasoning | ByteDance | 128000 | $14.56 | 81.6 |
| Gemini 2.5 Pro | Google DeepMind | 200000 | $15.20 | 81.6 |
| Llama 4 Maverick | Meta AI | 200000 | $5.36 | 81.6 |
FAQ
How much does Claude 3.7 Sonnet cost?
Claude 3.7 Sonnet is listed at $14.91 per million input tokens and $74.27 per million output tokens. Cached input is $1.70 per million tokens. A blended 3:1 input-to-output mix is about $29.75 per million tokens.
What is the context window of Claude 3.7 Sonnet?
Claude 3.7 Sonnet has a context window of 200,000 tokens and can emit up to 128,000 output tokens per request in this index.
Is Claude 3.7 Sonnet open weights?
No. Claude 3.7 Sonnet is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Claude 3.7 Sonnet score on benchmarks?
Claude 3.7 Sonnet averages 81.6 across the scored benchmarks in this index, ranking #91 of 600 models. Its strongest relative result is Arena Elo at 1451.9.
What is Claude 3.7 Sonnet best for?
Claude 3.7 Sonnet is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $14.91 per million input tokens, it sits in the mid-range of the index, and the 200,000-token context window is enough for large files and multi-file diffs.