Claude Sonnet 5.5 (Xhigh, Default Fallback) vs gpt-oss-120b (High)
Which is better for the money: Claude Sonnet 5.5 (Xhigh, 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.
Depends on your budget
Claude Sonnet 5.5 (Xhigh, Default Fallb… scores 40.3 points higher (51.9 vs 11.6) but costs 18× as much to run the benchmark ($2177 vs $123; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Claude Sonnet 5.5 (Xhigh, Default Fallb… when you need intelligence above 11.6, and gpt-oss-120b (High) when 11.6 is enough.
| Metric | Claude Sonnet 5.5 (Xhigh, Default Fallback) | gpt-oss-120b (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 51.9 | 11.6 | −77.6% gpt-oss-120b (High) is 77.6% less intelligent |
| Total AA cost (lower is better) | $2,176.82 | $122.71 | −94.4% gpt-oss-120b (High) is 94.4% cheaper |
| End-to-end time (lower is better) | 33.91s | 11.19s | −67.0% gpt-oss-120b (High) is 67.0% faster |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $0.15 / $0.60 | |
| Input modalities | Text, Image | Text |
gpt-oss-120b (High) vs Claude Sonnet 5.5 (Xhigh, Default Fallback): 77.6% less intelligence, 94.4% less cost to run the AA benchmark, and 67.0% faster end-to-end.
Against the frontier
- Claude Sonnet 5.5 (Xhigh, Default Fallback) is off the frontier: at the same or lower cost, Claude Opus 5.5 (High, Default Fallback) scores 53.60 for $2172.
- gpt-oss-120b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
Compare something else
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/claude-sonnet-5-5-xhigh/gpt-oss-120b · Markdown: /api/v1/compare/claude-sonnet-5-5-xhigh/gpt-oss-120b?format=md · llms.txt · agent skill