Compare openai/gpt-4.1-nano vs anthropic/claude-3.5-haiku

Model Comparison

Metric	gpt-4.1-nano openai	claude-3.5-haiku anthropic
Pricing
Input Price	$0.1 / 1M tokens	$0.8 / 1M tokens
Output Price	$0.4 / 1M tokens	$4 / 1M tokens
Capabilities
Context Window	1047576 tokens	200K tokens
Capabilities	tools	tools
Input type	text, image	text, image
Category Scores
Overall Average	52.3	42.7
Science	51.2	45.6
Vision	55.4	N/A
Writing	50.3	44.8
Academia	N/A	30.7
Marketing	N/A	49.8
Benchmark Tests
AIME	_	3.3
AAII	_	20.2
DROP	_	83.1
GPQA	50.3	41.2
HLE	_	3.5
HumanEval	_	88.1
LiveCodeBench	_	31.4
MATH-500	_	72.1
MMLU-Pro	_	63.4
MMMU	55.4	_
SciCode	_	27.4

gpt-4.1-nano Advantages

• Higher benchmark scores (52.3 vs 42.7)
• Lower input token cost ($0.1 / 1M tokens vs $0.8 / 1M tokens)
• Larger context window (1047576 tokens vs 200K tokens)

claude-3.5-haiku Advantages

Compare openai/gpt-4.1-nano vs anthropic/claude-3.5-haiku