Compare anthropic/claude-sonnet-4 vs deepinfra/llama-3.2-1b-instruct

Model Comparison

Metric	claude-sonnet-4 anthropic	llama-3.2-1b-instruct deepinfra
Pricing
Input Price	$3 / 1M tokens	<$0.01 / 1M tokens
Output Price	$15 / 1M tokens	$0.01 / 1M tokens
Capabilities
Context Window	200K tokens	131072 tokens
Capabilities	tools
Input type	text, image	text
Category Scores
Overall Average	64.9	0.0
Maths	74.3	N/A
Finance	65.4	N/A
Science	72.7	N/A
Writing	63.5	N/A
Academia	67.1	N/A
Marketing	66.4	N/A
Programming	45.1	N/A
Benchmark Tests
HLE	9.6	_
AIME	77.3	_
GPQA	77.7	_
SciCode	40.0	_
MATH-500	99.1	_
MMLU-Pro	84.2	_
LiveCodeBench	65.5	_
AA Math Index	74.3	_
AA Coding Index	45.1	_
AAII	56.5	_

claude-sonnet-4 Advantages

• Higher benchmark scores (64.9 vs 0.0)
• Larger context window (200K tokens vs 131072 tokens)

llama-3.2-1b-instruct Advantages

• Lower input token cost (<$0.01 / 1M tokens vs $3 / 1M tokens)

Compare anthropic/claude-sonnet-4 vs deepinfra/llama-3.2-1b-instruct