Back to GalleryBack

Model Comparison

gpt-oss-20bvsclaude-opus-4

Model Comparison

Compare performance, benchmarks, and characteristics

gpt-oss-20b

deepinfra

Context131072 tokens

Input Price$0.04 / 1M tokens

Output Price$0.16 / 1M tokens

View Details →

claude-opus-4

anthropic

Context200K tokens

Input Price$15 / 1M tokens

Output Price$75 / 1M tokens

View Details →

Loading comparison...

Model Comparison

Metric	gpt-oss-20b deepinfra	claude-opus-4 anthropic
Pricing
Input Price	$0.04 / 1M tokens	$15 / 1M tokens
Output Price	$0.16 / 1M tokens	$75 / 1M tokens
Capabilities
Context Window	131072 tokens	200K tokens
Capabilities	tools	tools
Input type	text	text, image
Category Scores
Overall Average	48.4	55.9
Academia	58.1	70.1
Marketing	32.7	43.5
Programming	53.7	53.1
Science	71.5	80.9
Writing	25.9	32.0
Benchmark Tests
AA Coding Index	53.7	53.1
AAII	44.8	59.3
GPQA	71.5	80.9
HLE	8.5	11.9
LiveCodeBench	72.1	65.4
MMLU-Pro	73.6	88.0
SciCode	35.4	40.9

gpt-oss-20b Advantages

• Lower input token cost ($0.04 / 1M tokens vs $15 / 1M tokens)

claude-opus-4 Advantages

• Higher benchmark scores (55.9 vs 48.4)
• Larger context window (200K tokens vs 131072 tokens)

Compare deepinfra/gpt-oss-20b vs anthropic/claude-opus-4