Model Comparison

DeepSeek-R1-Distill-Llama-70Bvsclaude-sonnet-4

Compare performance, benchmarks, and characteristics

togetherai

Context131072 tokens

Input Price$2 / 1M tokens

Output Price$2 / 1M tokens

anthropic

Context200K tokens

Input Price$3 / 1M tokens

Output Price$15 / 1M tokens

Model Comparison

Metric	DeepSeek-R1-Distill-Llama-70B togetherai	claude-sonnet-4 anthropic
Pricing
Input Price	$2 / 1M tokens	$3 / 1M tokens
Output Price	$2 / 1M tokens	$15 / 1M tokens
Capabilities
Context Window	131072 tokens	200K tokens
Capabilities		tools
Input type	text	text, image
Category Scores
Overall Average	45.9	53.5
Academia	48.0	59.9
Finance	55.5	55.7
Marketing	22.6	30.9
Maths	80.2	67.0
Programming	28.9	41.1
Science	65.2	75.4
Writing	21.2	23.7
Vision	N/A	74.4
Benchmark Tests
AIME	67.0	40.7
AA Coding Index	28.9	41.1
AAII	30.8	44.4
AA Math Index	80.2	67.0
GPQA	65.2	75.4
HLE	6.1	4.0
LiveCodeBench	26.6	44.9
MATH-500	93.5	93.4
MMLU-Pro	79.5	83.7
MMMU	_	74.4
SciCode	31.2	37.3

DeepSeek-R1-Distill-Llama-70B Advantages

claude-sonnet-4 Advantages

Loading comparison...

Model Comparison

Metric	DeepSeek-R1-Distill-Llama-70B togetherai	claude-sonnet-4 anthropic
Pricing
Input Price	$2 / 1M tokens	$3 / 1M tokens
Output Price	$2 / 1M tokens	$15 / 1M tokens
Capabilities
Context Window	131072 tokens	200K tokens
Capabilities		tools
Input type	text	text, image
Category Scores
Overall Average	45.9	53.5
Academia	48.0	59.9
Finance	55.5	55.7
Marketing	22.6	30.9
Maths	80.2	67.0
Programming	28.9	41.1
Science	65.2	75.4
Writing	21.2	23.7
Vision	N/A	74.4
Benchmark Tests
AIME	67.0	40.7
AA Coding Index	28.9	41.1
AAII	30.8	44.4
AA Math Index	80.2	67.0
GPQA	65.2	75.4
HLE	6.1	4.0
LiveCodeBench	26.6	44.9
MATH-500	93.5	93.4
MMLU-Pro	79.5	83.7
MMMU	_	74.4
SciCode	31.2	37.3

DeepSeek-R1-Distill-Llama-70B Advantages

claude-sonnet-4 Advantages