Model Comparison

DeepSeek-R1-Distill-Llama-70Bvsclaude-opus-4.5

Compare performance, benchmarks, and characteristics

deepinfra

Context131072 tokens

Input Price$0.5 / 1M tokens

Output Price$1 / 1M tokens

anthropic

Context200K tokens

Input Price$5 / 1M tokens

Output Price$25 / 1M tokens

Model Comparison

Metric	DeepSeek-R1-Distill-Llama-70B deepinfra	claude-opus-4.5 anthropic
Pricing
Input Price	$0.5 / 1M tokens	$5 / 1M tokens
Output Price	$1 / 1M tokens	$25 / 1M tokens
Capabilities
Context Window	131072 tokens	200K tokens
Capabilities
Input type	text	text, image
Category Scores
Overall Average	43.5	76.6
Maths	53.7	91.3
Finance	41.8	80.5
Science	64.2	81.3
Writing	39.9	71.2
Academia	47.5	78.2
Marketing	37.7	73.3
Programming	19.7	60.2
Benchmark Tests
HLE	6.1	28.4
AIME	67.0	_
GPQA	65.2	86.6
SciCode	31.2	49.5
MATH-500	93.5	_
MMLU-Pro	79.5	89.5
LiveCodeBench	26.6	87.1
AA Math Index	53.7	91.3
AA Coding Index	19.7	60.2
AAII	29.9	69.8

DeepSeek-R1-Distill-Llama-70B Advantages

claude-opus-4.5 Advantages

Loading comparison...

Model Comparison

Metric	DeepSeek-R1-Distill-Llama-70B deepinfra	claude-opus-4.5 anthropic
Pricing
Input Price	$0.5 / 1M tokens	$5 / 1M tokens
Output Price	$1 / 1M tokens	$25 / 1M tokens
Capabilities
Context Window	131072 tokens	200K tokens
Capabilities
Input type	text	text, image
Category Scores
Overall Average	43.5	76.6
Maths	53.7	91.3
Finance	41.8	80.5
Science	64.2	81.3
Writing	39.9	71.2
Academia	47.5	78.2
Marketing	37.7	73.3
Programming	19.7	60.2
Benchmark Tests
HLE	6.1	28.4
AIME	67.0	_
GPQA	65.2	86.6
SciCode	31.2	49.5
MATH-500	93.5	_
MMLU-Pro	79.5	89.5
LiveCodeBench	26.6	87.1
AA Math Index	53.7	91.3
AA Coding Index	19.7	60.2
AAII	29.9	69.8

DeepSeek-R1-Distill-Llama-70B Advantages

claude-opus-4.5 Advantages