Model Comparison

kimi-linear-48b-a3b-instructvsclaude-opus-4

Compare performance, benchmarks, and characteristics

openrouter

Context1048576 tokens

Input Price$0.3 / 1M tokens

Output Price$0.6 / 1M tokens

anthropic

Context200K tokens

Input Price$15 / 1M tokens

Output Price$75 / 1M tokens

Model Comparison

Metric	kimi-linear-48b-a3b-instruct openrouter	claude-opus-4 anthropic
Pricing
Input Price	$0.3 / 1M tokens	$15 / 1M tokens
Output Price	$0.6 / 1M tokens	$75 / 1M tokens
Capabilities
Context Window	1048576 tokens	200K tokens
Capabilities		tools
Input type	text	text, image
Category Scores
Overall Average	33.9	62.5
Maths	36.3	73.3
Finance	31.2	63.8
Science	43.6	75.0
Writing	34.5	56.8
Academia	33.6	66.9
Marketing	35.4	57.4
Programming	22.8	44.2
Benchmark Tests
HLE	2.7	11.7
AIME	_	75.7
GPQA	41.2	79.6
SciCode	19.9	39.8
MATH-500	_	98.2
MMLU-Pro	58.5	87.3
LiveCodeBench	37.8	63.6
AA Math Index	36.3	73.3
AA Coding Index	22.8	44.2
AAII	26.1	54.2

kimi-linear-48b-a3b-instruct Advantages

claude-opus-4 Advantages

Loading comparison...

Model Comparison

Metric	kimi-linear-48b-a3b-instruct openrouter	claude-opus-4 anthropic
Pricing
Input Price	$0.3 / 1M tokens	$15 / 1M tokens
Output Price	$0.6 / 1M tokens	$75 / 1M tokens
Capabilities
Context Window	1048576 tokens	200K tokens
Capabilities		tools
Input type	text	text, image
Category Scores
Overall Average	33.9	62.5
Maths	36.3	73.3
Finance	31.2	63.8
Science	43.6	75.0
Writing	34.5	56.8
Academia	33.6	66.9
Marketing	35.4	57.4
Programming	22.8	44.2
Benchmark Tests
HLE	2.7	11.7
AIME	_	75.7
GPQA	41.2	79.6
SciCode	19.9	39.8
MATH-500	_	98.2
MMLU-Pro	58.5	87.3
LiveCodeBench	37.8	63.6
AA Math Index	36.3	73.3
AA Coding Index	22.8	44.2
AAII	26.1	54.2

kimi-linear-48b-a3b-instruct Advantages

claude-opus-4 Advantages