Compare anthropic/claude-opus-4.5 vs deepinfra/mistral-nemo

Model Comparison

Metric	claude-opus-4.5 anthropic	mistral-nemo deepinfra
Pricing
Input Price	$5 / 1M tokens	$0.02 / 1M tokens
Output Price	$25 / 1M tokens	$0.04 / 1M tokens
Capabilities
Context Window	200K tokens	131072 tokens
Capabilities
Input type	text, image	text
Category Scores
Overall Average	76.6	27.6
Maths	91.3	N/A
Finance	80.5	N/A
Science	81.3	31.7
Writing	71.2	30.3
Academia	78.2	18.3
Marketing	73.3	30.2
Programming	60.2	N/A
Benchmark Tests
HLE	28.4	4.4
AIME	_	0.3
GPQA	86.6	31.4
MMLU	_	68.0
SciCode	49.5	10.4
MATH-500	_	39.5
MMLU-Pro	89.5	39.9
LiveCodeBench	87.1	5.7
AA Math Index	91.3	_
AA Coding Index	60.2	_
AAII	69.8	5.2

claude-opus-4.5 Advantages

• Higher benchmark scores (76.6 vs 27.6)
• Larger context window (200K tokens vs 131072 tokens)

mistral-nemo Advantages

• Lower input token cost ($0.02 / 1M tokens vs $5 / 1M tokens)

Compare anthropic/claude-opus-4.5 vs deepinfra/mistral-nemo