Anthropic
Anthropic
Multimodal model · United States ·Jun 2024

Claude 3.5 Sonnet

Multimodal Proprietary
39
Benchmarks

About Claude 3.5 Sonnet

Claude 3.5 Sonnet is an AI model developed by Anthropic, in the multimodal category, released in 2024, made available as a proprietary (API-only) model.

On this page you'll find Claude 3.5 Sonnet's full specifications, including 39 benchmark results. Review provider pricing and benchmark scores below, or compare Claude 3.5 Sonnet head-to-head with other multimodal models.

Links

Community

Would you run Claude 3.5 Sonnet again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

Claude 3.5 Sonnet benchmark scores
Benchmark Category Score Variant
HumanEval code 93.7% 1022-cited-minimax-text
HumanEval code 92% cited-nvlm
LiveCodeBench v5 code 38.9% 1022-cited-mimo
LiveCodeBench v6 code 37.2% 1022-cited-mimo
MBPP+ code 75.1% 1022-plus-cited-minimax-text
ArenaHard general 87.6% 1022-cited-minimax-text
ArenaHard general 79.3% cited-athene
IFEval general 90.1% 1022-avg-cited-minimax-text
IFEval general 86.5% 1022-cited-mimo
MMLU general 88.7% cited-nvlm
MMLU general 88.3% 1022-cited-minimax-text
MMLU-Pro general 78% 1022-cited-mimo
MMLU-Pro general 78% 1022-cited-minimax-text
SuperGPQA knowledge 48.2 1022-cited-mimo
AIME 2024 math 16% 1022-cited-mimo
AIME 2024 math 13.3% 1022-cited-oreal
AIME 2025 math 7.4% 1022-cited-mimo
GSM8K math 96.9% 1022-cited-minimax-text
GSM8K math 96.4% cited-nvlm
MATH math 74.1% 1022-cited-minimax-text
MATH math 71.1% cited-nvlm
MATH-500 math 78.3% 1022-cited-oreal
MATH-500 math 78.3% 1022-cited-mimo
ChartQA multimodal 90.8% cited-nvlm
ChartQA multimodal 89.1% cot-cited-pixtral-large
DocVQA multimodal 95.200 cited-nvlm
DocVQA multimodal 88.600 anls-cited-pixtral-large
MMMU multimodal 70.4% 20241022-val-cited-qvq
MMMU multimodal 68.4% cot-cited-pixtral-large
MMMU multimodal 68.3% val-cited-nvlm
MathVista multimodal 67.7% cited-nvlm
MathVista multimodal 67.1% cot-cited-pixtral-large
MathVista multimodal 65.3% 20241022-mini-cited-qvq
DROP reasoning 88.8% 1022-f1-cited-minimax-text
DROP reasoning 88.3% 1022-cited-mimo
GPQA Diamond reasoning 65% 1022-cited-mimo
GPQA Diamond reasoning 65% 1022-diamond-cited-minimax-text
C-SimpleQA safety 56.8% 1022-cited-minimax-text
SimpleQA safety 28.1% 1022-cited-minimax-text

More models like Claude 3.5 Sonnet

Frequently asked questions

What is Claude 3.5 Sonnet?

Claude 3.5 Sonnet is an AI model developed by Anthropic, in the multimodal category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Claude 3.5 Sonnet?

Claude 3.5 Sonnet was developed by Anthropic and released in 2024.

Is Claude 3.5 Sonnet open source or proprietary?

Claude 3.5 Sonnet is a proprietary model. It is accessed through an API rather than by downloading the weights.

How much does Claude 3.5 Sonnet cost?

Pricing for Claude 3.5 Sonnet depends on the provider. See the providers table on this page for the latest API rates.

How does Claude 3.5 Sonnet perform on benchmarks?

Claude 3.5 Sonnet is benchmarked across 39 evaluations on GenAIList, including HumanEval (93.7%). See the full benchmark table below and compare it with other models.

No videos yet. Know a good one? Add it below.

Know a great video about Claude 3.5 Sonnet?