Claude 3.7 Sonnet
ProprietaryMultimodalHighlight
About
Claude 3.7 Sonnet is Anthropic's advanced model with extended thinking capabilities, offering state-of-the-art reasoning for complex tasks.
Capabilities
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution
Providers(4)
Compare all →| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Snowflake Cortex | — | — | Serverless | |
| GCP Vertex AI | $3 | $15 | Serverless | |
| Replicate API | $3 | $15 | Serverless | |
| OpenRouter | $3 | $15 | Serverless |
Benchmark Scores(6)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| HumanEval | 93.0 | 2025-02 | Anthropic |
| SWE-bench Verified | 70.3 | 2025-02 | Anthropic |
| LiveCodeBench | 68.9 | 2025-02 | Anthropic |
| Aider Polyglot | 64.9 | 2026-04 (32k thinking tokens) | https://aider.chat/docs/leaderboards |
| Massive Multi-discipline Multimodal Understanding | 75.0 | — | https://mmmu-benchmark.github.io/ |
| MMLU PRO | 80.3 | — | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro |
API Versions
claude-3-7-sonnet-20250219Rankings
Specifications
FamilyClaude 3.7
Released2024-03-04
Context200K
ArchitectureDecoder Only
Knowledge cutoff2024-11
Specializationgeneral
Trainingfinetuning
Created by
Developing safe and ethical AI systems.
San Francisco, California, United States
Founded 2021
Website