Model Comparison

claude-sonnet-4.5vsDeepSeek-R1-Distill-Llama-70B

Compare performance, benchmarks, and characteristics

anthropic

Context200K tokens

Input Price$3 / 1M tokens

Output Price$15 / 1M tokens

deepinfra

Context131072 tokens

Input Price$0.5 / 1M tokens

Output Price$1 / 1M tokens

Model Comparison

Metric	claude-sonnet-4.5 anthropic	DeepSeek-R1-Distill-Llama-70B deepinfra
Pricing
Input Price	$3 / 1M tokens	$0.5 / 1M tokens
Output Price	$15 / 1M tokens	$1 / 1M tokens
Capabilities
Context Window	200K tokens	131072 tokens
Capabilities	tools, reasoning
Input type	text, image	text
Category Scores
Overall Average	71.4	43.5
Maths	88.0	53.7
Finance	75.3	41.8
Science	77.7	64.2
Writing	66.9	39.9
Academia	73.0	47.5
Marketing	69.2	37.7
Programming	49.8	19.7
Benchmark Tests
HLE	17.3	6.1
AIME	_	67.0
GPQA	83.4	65.2
SciCode	44.7	31.2
MATH-500	_	93.5
MMLU-Pro	87.5	79.5
LiveCodeBench	71.4	26.6
AA Math Index	88.0	53.7
AA Coding Index	49.8	19.7
AAII	62.7	29.9

claude-sonnet-4.5 Advantages

DeepSeek-R1-Distill-Llama-70B Advantages

Loading comparison...

Model Comparison

Metric	claude-sonnet-4.5 anthropic	DeepSeek-R1-Distill-Llama-70B deepinfra
Pricing
Input Price	$3 / 1M tokens	$0.5 / 1M tokens
Output Price	$15 / 1M tokens	$1 / 1M tokens
Capabilities
Context Window	200K tokens	131072 tokens
Capabilities	tools, reasoning
Input type	text, image	text
Category Scores
Overall Average	71.4	43.5
Maths	88.0	53.7
Finance	75.3	41.8
Science	77.7	64.2
Writing	66.9	39.9
Academia	73.0	47.5
Marketing	69.2	37.7
Programming	49.8	19.7
Benchmark Tests
HLE	17.3	6.1
AIME	_	67.0
GPQA	83.4	65.2
SciCode	44.7	31.2
MATH-500	_	93.5
MMLU-Pro	87.5	79.5
LiveCodeBench	71.4	26.6
AA Math Index	88.0	53.7
AA Coding Index	49.8	19.7
AAII	62.7	29.9

claude-sonnet-4.5 Advantages

DeepSeek-R1-Distill-Llama-70B Advantages