GPT-5.5 (High) vs GPT-5 mini (High)
Which is better for the money: GPT-5.5 (High) by OpenAI or GPT-5 mini (High) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
GPT-5.5 (High) scores 20.2 points higher (37.0 vs 16.8) but costs 18× as much to run the benchmark ($3411 vs $189; flagship vs mid-range cost classes). They are not alternatives at one budget: pick GPT-5.5 (High) when you need intelligence above 16.8, and GPT-5 mini (High) when 16.8 is enough.
| Metric | GPT-5.5 (High) | GPT-5 mini (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 37.0 | 16.8 | −54.6% GPT-5 mini (High) is 54.6% less intelligent |
| Total AA cost (lower is better) | $3,410.76 | $188.66 | −94.5% GPT-5 mini (High) is 94.5% cheaper |
| End-to-end time (lower is better) | 20.37s | 58.74s | +188.4% GPT-5 mini (High) is 188.4% slower |
| Price per 1M tokens (in / out) | $5.00 / $30.0 | $0.25 / $2.00 | |
| Input modalities | Text, Image | Text, Image |
GPT-5 mini (High) vs GPT-5.5 (High): 54.6% less intelligence, 94.5% less cost to run the AA benchmark, and 188.4% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-5.5 (High) is off the frontier: at the same or lower cost, Kimi K3.1 Pro scores 55.10 for $3117.
- GPT-5 mini (High) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Xhigh) scores 41.20 for $158.
GPT-5.5 (High)GPT-5 mini (High)Today's Pareto frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/gpt-5-5-high/gpt-5-mini · Markdown: /api/v1/compare/gpt-5-5-high/gpt-5-mini?format=md · llms.txt · agent skill