Back to GalleryBack

Model Comparison

gemma-2-27b-itvsclaude-sonnet-4.5

Model Comparison

Compare performance, benchmarks, and characteristics

gemma-2-27b-it

togetherai

Context8192 tokens

Input Price$0.3 / 1M tokens

Output Price$0.3 / 1M tokens

View Details →

claude-sonnet-4.5

anthropic

Context200K tokens

Input Price$3 / 1M tokens

Output Price$15 / 1M tokens

View Details →

Loading comparison...

Model Comparison

Metric	gemma-2-27b-it togetherai	claude-sonnet-4.5 anthropic
Pricing
Input Price	$0.3 / 1M tokens	$3 / 1M tokens
Output Price	$0.3 / 1M tokens	$15 / 1M tokens
Capabilities
Context Window	8192 tokens	200K tokens
Capabilities		tools, reasoning
Input type	text	text, image
Category Scores
Overall Average	34.4	0.0
Academia	26.4	N/A
Marketing	44.7	N/A
Programming	20.2	N/A
Science	40.6	N/A
Writing	40.2	N/A
Benchmark Tests
AIME	29.7	_
AA Coding Index	20.2	_
AAII	17.2	_
GPQA	35.7	_
HLE	3.7	_
HumanEval	51.8	_
LiveCodeBench	27.9	_
MATH-500	54.1	_
MMLU	75.2	_
MMLU-Pro	57.5	_
SciCode	12.5	_

gemma-2-27b-it Advantages

• Higher benchmark scores (34.4 vs 0.0)
• Lower input token cost ($0.3 / 1M tokens vs $3 / 1M tokens)

claude-sonnet-4.5 Advantages

• Larger context window (200K tokens vs 8192 tokens)

Compare togetherai/gemma-2-27b-it vs anthropic/claude-sonnet-4.5