Compare deepinfra/llama-3-8b-instruct vs gemini/gemini-3-flash-preview

Model Comparison

Metric	llama-3-8b-instruct deepinfra	gemini-3-flash-preview gemini
Pricing
Input Price	$0.03 / 1M tokens	$0.5 / 1M tokens
Output Price	$0.06 / 1M tokens	$3 / 1M tokens
Capabilities
Context Window	8192 tokens	1M tokens
Capabilities	tools	tools, reasoning
Input type	text	text, image, audio, video
Category Scores
Overall Average	0.0	63.3
Maths	N/A	55.7
Finance	N/A	55.1
Science	N/A	81.1
Writing	N/A	62.8
Academia	N/A	72.5
Marketing	N/A	63.0
Programming	N/A	53.1
Benchmark Tests
HLE	_	14.1
GPQA	_	90.4
SciCode	_	49.9
MMLU-Pro	_	88.2
LiveCodeBench	_	79.7
AA Math Index	_	55.7
AA Coding Index	_	53.1
AAII	_	54.5

llama-3-8b-instruct Advantages

• Lower input token cost ($0.03 / 1M tokens vs $0.5 / 1M tokens)

gemini-3-flash-preview Advantages

• Higher benchmark scores (63.3 vs 0.0)
• Larger context window (1M tokens vs 8192 tokens)

Compare deepinfra/llama-3-8b-instruct vs gemini/gemini-3-flash-preview