Compare deepinfra/qwen-2.5-72b-instruct vs anthropic/claude-opus-4.5

Model Comparison

Metric	qwen-2.5-72b-instruct deepinfra	claude-opus-4.5 anthropic
Pricing
Input Price	$0.12 / 1M tokens	$5 / 1M tokens
Output Price	$0.39 / 1M tokens	$25 / 1M tokens
Capabilities
Context Window	32768 tokens	200K tokens
Capabilities	tools
Input type	text	text, image
Category Scores
Overall Average	32.5	76.6
Maths	14.0	91.3
Finance	21.5	80.5
Science	52.8	81.3
Writing	40.0	71.2
Academia	39.0	78.2
Marketing	40.4	73.3
Programming	19.5	60.2
Benchmark Tests
HLE	4.2	28.4
AIME	16.0	_
GPQA	49.0	86.6
SciCode	26.7	49.5
MATH-500	85.8	_
MMLU-Pro	71.5	89.5
HumanEval	86.6	_
LiveCodeBench	27.6	87.1
AA Math Index	14.0	91.3
AA Coding Index	19.5	60.2
AAII	29.0	69.8

qwen-2.5-72b-instruct Advantages

• Lower input token cost ($0.12 / 1M tokens vs $5 / 1M tokens)

claude-opus-4.5 Advantages

• Higher benchmark scores (76.6 vs 32.5)
• Larger context window (200K tokens vs 32768 tokens)

Compare deepinfra/qwen-2.5-72b-instruct vs anthropic/claude-opus-4.5