Claude Opus 5.5 (Medium, Default Fallback) vs gpt-oss-120b (High)

Which is better for the money: Claude Opus 5.5 (Medium, Default Fallback) by Anthropic or gpt-oss-120b (High) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.

Trade-off

AnthropicClaude Opus 5.5 (Medium, Default Fallback)Off the frontier

Intelligence: 51.20
Total cost: $1627

OpenAIgpt-oss-120b (High)Off the frontier

Intelligence: 11.60
Total cost: $123

Verdict

Depends on your budget

Claude Opus 5.5 (Medium, Default Fallba… scores 39.6 points higher (51.2 vs 11.6) but costs 13× as much to run the benchmark ($1627 vs $123; premium vs mid-range cost classes). They are not alternatives at one budget: pick Claude Opus 5.5 (Medium, Default Fallba… when you need intelligence above 11.6, and gpt-oss-120b (High) when 11.6 is enough.

Metric	Claude Opus 5.5 (Medium, Default Fallback)	gpt-oss-120b (High)	Difference
Intelligence (higher is better)	51.2	11.6	−77.3% gpt-oss-120b (High) is 77.3% less intelligent
Total AA cost (lower is better)	$1,626.81	$122.71	−92.5% gpt-oss-120b (High) is 92.5% cheaper
End-to-end time (lower is better)	21.78s	11.29s	−48.2% gpt-oss-120b (High) is 48.2% faster
Price per 1M tokens (in / out)	$4.00 / $20.0	$0.15 / $0.60
Input modalities	Text, Image	Text

gpt-oss-120b (High) vs Claude Opus 5.5 (Medium, Default Fallback): 77.3% less intelligence, 92.5% less cost to run the AA benchmark, and 48.2% faster end-to-end.

Open this matchup in the interactive picker Claude Opus 5.5 (Medium, Default Fallback): what beats it gpt-oss-120b (High): what beats it

Today's Pareto frontier

Against the frontier

Claude Opus 5.5 (Medium, Default Fallback) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
gpt-oss-120b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.

Claude Opus 5.5 (Medium, Default Fallback)gpt-oss-120b (High)Today's Pareto frontierOpen-weights frontierEvery other model

Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/claude-opus-5-5-medium/gpt-oss-120b · Markdown: /api/v1/compare/claude-opus-5-5-medium/gpt-oss-120b?format=md · llms.txt · agent skill