Compare anthropic/claude-3-5-sonnet-20240620 vs openai/gpt-4-0314

Model Comparison

Metric	claude-3-5-sonnet-20240620 anthropic	gpt-4-0314 openai
Pricing
Input Price	$3 / 1M tokens	$30 / 1M tokens
Output Price	$15 / 1M tokens	$60 / 1M tokens
Capabilities
Context Window	200K tokens	8191 tokens
Capabilities	tools	tools
Input type	text, image	text
Category Scores
Overall Average	51.1	0.0
Academia	44.8	N/A
Marketing	63.2	N/A
Programming	30.2	N/A
Science	60.3	N/A
Writing	57.3	N/A
Benchmark Tests
AIME	15.7	_
AA Coding Index	30.2	_
AAII	29.9	_
DROP	87.1	_
GPQA	59.7	_
HLE	3.9	_
HumanEval	92.0	_
LiveCodeBench	38.1	_
MATH-500	77.1	_
MMLU-Pro	77.2	_
SciCode	36.6	_

claude-3-5-sonnet-20240620 Advantages

• Higher benchmark scores (51.1 vs 0.0)
• Lower input token cost ($3 / 1M tokens vs $30 / 1M tokens)
• Larger context window (200K tokens vs 8191 tokens)

gpt-4-0314 Advantages

Compare anthropic/claude-3-5-sonnet-20240620 vs openai/gpt-4-0314