Claude 3.7 Sonnet vs Claude Sonnet 5
Compare Claude 3.7 Sonnet and Claude Sonnet 5 side-by-side. See how these vision models stack up in Open Prompt, OCR, Object Detection, Classification, and Image Captioning.
Compare Claude 3.7 Sonnet vs Claude Sonnet 5 live
Run the same image across every model that supports a task and compare their outputs side-by-side.
Detect and compare bounding boxes across models on the same image.
Upload an image
Drag and drop an image here, or click to browse
Claude 3.7 Sonnet is deprecated and can no longer be run. Details and evals are still available on its model page.
Models in this comparison
Claude 3.7 Sonnet vs Claude Sonnet 5 Comparison Table
Evals updated August 6, 2026Pricing updated August 7, 2026
| Property | Claude 3.7 Sonnet | Claude Sonnet 5 |
|---|---|---|
| Organization | Anthropic | Anthropic |
| Category | closed | closed |
| Modality | multimodal | multimodal |
| Release Date | Feb 2024 | Jun 2026 |
| Context Window | 200K | 1.0M |
| Parameters | ||
| License | Proprietary | Proprietary |
| Pricing per 1M tokens | ||
| Input $/1M | $2.00 | |
| Output $/1M | $10.00 | |
| Vision Tasks | ||
| Captioning | Demo | |
| Chart Question Answering | ||
| Classification | Demo | |
| Document Question Answering | ||
| Image Tagging | ||
| Multi-Label Classification | ||
| Object Detection | Demo | |
| OCR | Demo | |
| Vision Language | ||
| Visual Question Answering | Demo | |
| Model Features | ||
| Foundation Vision | ||
| LLMs with Vision Capabilities | ||
| Multimodal Vision | ||
Vision Evalsground-truth scores across 6 vision tasks, pooled at low effort | ||
| Overall | Deprecated | 66.4% |
| Avg cost / sample | – | $0.0064 |
| Avg speed / sample | – | 4.84s |
| By task | ||
| Object Detection | – | 36.1% $0.011 |
| Counting | – | 56.8% $0.0030 |
| Identification | – | 81.3% $0.0027 |
| OCR | – | 91.7% $0.0078 |
| Data Extraction | – | 89.7% $0.0030 |
| Reasoning (low) | – | 43.0% $0.0032 |
| Reasoning (high) | – | 43.0% $0.0043 |
Claude 3.7 Sonnet vs Claude Sonnet 5: Overview
Claude 3.7 Sonnet, released by Anthropic in February 2025, is the company’s first hybrid reasoning model, combining fast response generation with an optional “extended thinking mode” that reveals longer, step-by-step reasoning. Like its predecessors, it is multimodal, handling both text and images, but expands its usability with up to 200,000 input tokens and up to 128,000 output tokens (64K generally available, 128K in beta). This makes it well-suited for analyzing large documents, codebases, or multi-turn conversations.
Typical applications include software development, research workflows, extended reasoning tasks, and enterprise-scale knowledge work where a trade-off between speed and visible reasoning is valuable.
Claude Sonnet 5 is a mid-tier large language model from Anthropic, released on June 30, 2026, as the latest model in the Sonnet series and a direct successor to Claude Sonnet 4.6. It is a hybrid reasoning model designed primarily for agentic workflows, software coding, and professional tasks. The model features a 1 million token context window, a 128k maximum output token limit, and runs adaptive thinking by default, giving API users fine-grained control over reasoning effort across five levels (low, medium, high, max, and extra-high). It uses an updated tokenizer shared with Opus 4.7 and later models, which produces approximately 30% more tokens for equivalent text compared to earlier Claude models. On benchmarks, Sonnet 5 scores 63.2% on agentic coding and 81.2% on OSWorld, narrowing the gap with Opus 4.8 while remaining at Sonnet-tier pricing.
The model supports text and image input with text output, and accepts tools including browsers and terminals for autonomous multi-step task execution. Anthropic's safety evaluations report that Sonnet 5 shows a lower rate of undesirable behaviors than Sonnet 4.6 and is generally safer in agentic contexts, with improved resistance to prompt injection and reduced sycophancy. Cybersecurity safeguards equivalent to those on Opus 4.7 and 4.8 are active, though Anthropic notes the model was not deliberately trained on cybersecurity tasks. The model is proprietary and API-only, with no open weights.