Claude 3.5 Sonnet
Claude 3.5 Sonnet is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, rag, and agents
- Workloads that can use a 200k context window
- Buyers comparing 4 tracked provider routes
Do not use it for
- Workloads where another current model has stronger sourced task evidence
- Family
- Claude 3.5
- Released
- 2024-06-20
- Context
- 200k
- Parameters
- 70B
- Architecture
- Decoder Only
- Knowledge cutoff
- 2024-04
- Specialization
- general
- Training
- finetuned
Cheapest of 6 routes · Anthropic · cache read $0.300
About
Claude 3.5 Sonnet, the latest in Anthropic's line of large language models, merges state-of-the-art reasoning, coding, and natural language understanding capabilities with advanced multi-modal processing. Released in October 2024, it excels in benchmarks against previous models and competitors, thanks to its scalable attention mechanisms and massive neural network architecture. Its dynamic routing enables specialization in various tasks, supporting applications from software development and data analysis to customer support and content creation. Users benefit from its "Artifacts" feature for real-time collaborative workflows and can access the model through platforms like Claude.ai and APIs at competitive pricing rates.
Claude 3.5 Sonnet is a model in the Claude 3.5 family. The structured metadata tracks a 200k-token context window, multimodal input, reasoning, function calling, structured outputs, and code execution. This page tracks provider routes through GCP Vertex AI, AWS Bedrock, Anthropic, and 3 more, with the cheapest tracked route listed at $3 input and $15 output per 1M tokens. Headline tracked benchmarks include HellaSwag 96.2, HumanEval 92.0, and Massive Multitask Language Understanding 88.7.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ D5 relevant benchmarks in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Q/$ D1 relevant benchmark in the decision map.
Provider price ladder
Compare all 6Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Cache | Route |
|---|---|---|---|---|
| Anthropic | $3.00 | $15.00 | read $0.300 / 5m $3.75 / 1h $6.00 | Serverless |
| AWS Bedrock | $3.00 | $15.00 | - | Serverless |
| GCP Vertex AI | $3.00 | $15.00 | - | Serverless |
| Replicate API | $3.00 | $15.00 | - | Serverless |
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(11)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| HellaSwag | 96.2 | 10-shot | https://crfm.stanford.edu/helm/classic/latest/ |
| HumanEval | 92.0 | pass@1 | https://crfm.stanford.edu/helm/classic/latest/ |
| Massive Multitask Language Understanding | 88.7 | 5-shot | https://crfm.stanford.edu/helm/classic/latest/ |
| SWE-bench Verified | 49.0 | 2024-10 | https://www.anthropic.com/news/raising-the-bar-on-swe-bench-verified-with-claude-3-5-sonnet |
| LiveCodeBench | 48.7 | 2026-04 | https://livecodebench.github.io/performances_generation.json |
| Aider Polyglot | 51.6 | 2026-04 | https://aider.chat/docs/leaderboards |
| BigCodeBench | 44.6 | 2025-01 (Instruct Pass@1) | https://bigcode-bench.github.io/results.json |
| Chatbot Arena | 1340.0 | — | https://lmarena.ai |
| Massive Multi-discipline Multimodal Understanding | 68.3 | — | https://mmmu-benchmark.github.io/ |
| MMLU PRO | 77.2 | — | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro |
| Mostly Basic Programming Problems+ | 78.8 | — | https://evalplus.github.io/leaderboard.html |
Migration checks
No linked migration route is available for this model yet.