Claude 3 Sonnet
Multimodal
Zero-eval
by Anthropic
About
Claude 3 Sonnet is a multimodal language model developed by Anthropic. It achieves strong performance with an average score of 73.8% across 11 benchmarks. It excels particularly in ARC-C (93.2%), GSM8k (92.3%), HellaSwag (89.0%). The model shows particular specialization in reasoning tasks with an average performance of 91.1%. It supports a 400K token context window for handling large documents. The model is available through 3 API providers. As a multimodal model, it can process and understand text, images, and other input formats seamlessly. Released in 2024, it represents Anthropic's latest advancement in AI technology.
Pricing Range
Input (per 1M)$3.00 -$3.00
Output (per 1M)$15.00 -$15.00
Providers3
Timeline
AnnouncedFeb 29, 2024
ReleasedFeb 29, 2024
Specifications
Capabilities
Multimodal
License & Family
License
Proprietary
Benchmark Performance Overview
Performance metrics and category breakdown
Overall Performance
11 benchmarks
Average Score
73.8%
Best Score
93.2%
High Performers (80%+)
5Performance Metrics
Max Context Window
400.0KAvg Throughput
87.3 tok/sAvg Latency
0msTop Categories
reasoning
91.1%
code
73.0%
math
73.0%
general
67.6%
Benchmark Performance
Top benchmark scores with normalized values (0-100%)
Ranking Across Benchmarks
Position relative to other models on each benchmark
ARC-C
Rank #5 of 31
#2Llama 3.1 70B Instruct
94.8%
#3Nova Pro
94.8%
#4Claude 3 Opus
96.4%
#5Claude 3 Sonnet
93.2%
#6Jamba 1.5 Large
93.0%
#7Nova Lite
92.4%
#8Mistral Small 3 24B Base
91.3%
GSM8k
Rank #18 of 46
#15Mistral Large 2
93.0%
#16Qwen3 235B A22B
94.4%
#17Gemma 3 12B
94.4%
#18Claude 3 Sonnet
92.3%
#19Nova Micro
92.3%
#20Kimi K2 Base
92.1%
#21Qwen2.5 7B Instruct
91.6%
HellaSwag
Rank #4 of 24
#1Gemini 1.5 Pro
93.3%
#2GPT-4
95.3%
#3Claude 3 Opus
95.4%
#4Claude 3 Sonnet
89.0%
#5Command R+
88.6%
#6Qwen2 72B Instruct
87.6%
#7Gemini 1.5 Flash
86.5%
MGSM
Rank #17 of 31
#14Qwen3 235B A22B
83.5%
#15Claude 3.5 Haiku
85.6%
#16Llama 3.2 90B Instruct
86.9%
#17Claude 3 Sonnet
83.5%
#18Gemini 1.5 Flash
82.6%
#19Phi 4
80.6%
#20Claude 3 Haiku
75.1%
BIG-Bench Hard
Rank #8 of 21
#5Gemini 1.5 Flash
85.5%
#6Gemma 3 12B
85.7%
#7Claude 3 Opus
86.8%
#8Claude 3 Sonnet
82.9%
#9Phi-3.5-MoE-instruct
79.1%
#10Claude 3 Haiku
73.7%
#11Gemma 3 4B
72.2%
All Benchmark Results for Claude 3 Sonnet
Complete list of benchmark scores with detailed information
ARC-C ARC-C benchmark | reasoning | text | 0.93 | 93.2% | Self-reported |
GSM8k GSM8k benchmark | math | text | 0.92 | 92.3% | Self-reported |
HellaSwag HellaSwag benchmark | reasoning | text | 0.89 | 89.0% | Self-reported |
MGSM MGSM benchmark | math | text | 0.83 | 83.5% | Self-reported |
BIG-Bench Hard BIG-Bench Hard benchmark | general | text | 0.83 | 82.9% | Self-reported |
MMLU MMLU benchmark | general | text | 0.79 | 79.0% | Self-reported |
DROP DROP benchmark | general | text | 0.79 | 78.9% | Self-reported |
HumanEval HumanEval benchmark | code | text | 0.73 | 73.0% | Self-reported |
MMLU-Pro MMLU-Pro benchmark | general | text | 0.57 | 56.8% | Self-reported |
MATH MATH benchmark | math | text | 0.43 | 43.1% | Self-reported |
Showing 1 to 10 of 11 benchmarks