Compare deepinfra/gpt-oss-20b vs anthropic/claude-opus-4.5

Model Comparison

Metric	gpt-oss-20b deepinfra	claude-opus-4.5 anthropic
Pricing
Input Price	$0.04 / 1M tokens	$5 / 1M tokens
Output Price	$0.16 / 1M tokens	$25 / 1M tokens
Capabilities
Context Window	131072 tokens	200K tokens
Capabilities	tools
Input type	text	text, image
Category Scores
Overall Average	62.8	76.6
Maths	89.3	91.3
Finance	70.8	80.5
Science	65.3	81.3
Writing	55.1	71.2
Academia	61.3	78.2
Marketing	57.3	73.3
Programming	40.7	60.2
Benchmark Tests
HLE	9.8	28.4
GPQA	70.2	86.6
MMLU	85.3	_
SciCode	34.4	49.5
MMLU-Pro	74.8	89.5
LiveCodeBench	77.7	87.1
AA Math Index	89.3	91.3
AA Coding Index	40.7	60.2
AAII	52.4	69.8

gpt-oss-20b Advantages

• Lower input token cost ($0.04 / 1M tokens vs $5 / 1M tokens)

claude-opus-4.5 Advantages

• Higher benchmark scores (76.6 vs 62.8)
• Larger context window (200K tokens vs 131072 tokens)

Compare deepinfra/gpt-oss-20b vs anthropic/claude-opus-4.5