LLMAPI only
Claude 3.5 Sonnet
Anthropic
Updated May 21, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error
Superseded by Claude 3.7 Sonnet
Specifications
- Type
- LLM
- Access
- API only
- Released
- June 20, 2024
- License
- Proprietary
- Context window
- 200,000 tokens
- Output speed
- 101 tok/s
- Latency (TTFT)
- 0.4s
- Input
- Text, Image
- Output
- Text
- API pricing
- $3.00 in · $15.00 out / 1M tokens
Capabilities
Function callingStructured output
Benchmarks
Reasoning
| BIG-Bench Hard | 93.1 |
| DROP | 87.1 |
| GPQA Diamond | 67.2 |
Coding
| HumanEval | 93.7 |
| SWE-bench Verified | 49 |
| LiveCodeBench | 38.1 |
Agents
General
| MMLU | 90.4 |
| MMLU-Pro | 77.6 |
| Humanity’s Last Exam | 3.9 |
Our take
The mid-tier model that punched above its weight — frontier-class coding and reasoning at a fraction of flagship pricing, plus the first version of computer use. For much of 2024 it was the default workhorse for developers.