LLMversus
Anthropic

Claude 3.5 Sonnet

Complete specs, pricing, and benchmark data for Claude 3.5 Sonnet by Anthropic. Last verified 2026-04-20.

MultimodalJSON ModeFunctionsStreaming
Pricing

Input / 1M tokens

$3.00

Output / 1M tokens

$15.00

Context & Output

Context Window

200K

Max Output

8,192

TTFT

150ms

Speed

100 tok/s

Benchmarks

Arena ELO

1270

Coding ELO

1300

Reasoning ELO

1270

HumanEval

92

MMLU

88.3

MATH

136

GPQA

60

Try Claude 3.5 Sonnet API

Start building with Claude 3.5 Sonnet

Get API Access→

Price History (Input $/M tokens)

Strengths
  • +Best coding
  • +Large context
  • +Strong reasoning
Limitations
  • -No code execution
  • -Premium pricing

Best For

CodingGeneral PurposeMultimodal

Compare Claude 3.5 Sonnet with...

vs Claude Opus 4vs Gemini 2.5 Provs o3vs DeepSeek R1vs o1vs Qwen 3 235B MoEvs Gemini Experimental 1206vs GPT-4.5vs DeepSeek R1 (Groq)vs Llama 4 Maverickvs DeepSeek R1 (Together)vs Grok 3
Official Pricing Page →
Your ad here