Responsible AI Use Disclaimer: The tools listed are for informational purposes. Users are responsible for adhering to ethical guidelines. Learn more.

Anthropic ProprietaryOct 2024

Claude 3.5 Sonnet

The model that made coding agents viable — still a top pick.

Intelligence index
71/ 100
vs all models59th pctile
Composite of MMLU, GPQA, MATH & HumanEval
Speed
85tok/s
vs all models41th pctile
Median across providers, steady state
Blended price
$6.00/ 1M tokens
vs all models27th pctile
3:1 input:output blend

At a glance

Context window
200k tokens
Max output
8k tokens
Input price
$3.00 / 1M tokens
Output price
$15.00 / 1M tokens
Time to first token
0.9s
Input modalities
text, image
Output modalities
text
License
Proprietary
Provider
Anthropic

Benchmark scores

Public scores from each provider; bars compare this model against the leader in each benchmark.

MMLU
General knowledge across 57 subjects
88.3
leader: 91.8
MMLU Pro
Harder MMLU successor with more reasoning
74.0
leader: 80.0
GPQA
Graduate-level science Q&A
59.4
leader: 78.0
MATH
Competition mathematics
78.3
leader: 94.8
HumanEval
Python code generation pass@1
92.0
leader: 95.8
Strengths
  • Excellent at code
  • Strong writing
  • Long context
Weaknesses
  • Superseded by Claude 4 Sonnet for new builds
Best for
  • Coding tasks
  • Long-form writing
  • Agentic workflows

Claude 3.5 Sonnet vs… popular head-to-heads

One-click matchups against the models people compare Claude 3.5 Sonnet with most.

Claude 3.5 Sonnet — frequently asked questions

Claude 3.5 Sonnet is a large language model from Anthropic, released on 22 October 2024. The model that made coding agents viable — still a top pick.

Need help choosing between models?

Compare every option in one sortable table — intelligence, speed and price on a single page.