GPT-5.4 mini (Xhigh) vs GPT-5.5 (High)
Which is better for the money: GPT-5.4 mini (Xhigh) by OpenAI or GPT-5.5 (High) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
GPT-5.5 (High) scores 12.9 points higher (37.0 vs 24.1) but costs 2.2× as much to run the benchmark ($3411 vs $1524; flagship vs premium cost classes). Pick GPT-5.5 (High) when the extra intelligence is worth the premium, otherwise GPT-5.4 mini (Xhigh).
| Metric | GPT-5.4 mini (Xhigh) | GPT-5.5 (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 24.1 | 37.0 | +53.5% GPT-5.5 (High) is 53.5% more intelligent |
| Total AA cost (lower is better) | $1,524.02 | $3,410.76 | +123.8% GPT-5.5 (High) is 2.2× more expensive |
| End-to-end time (lower is better) | 115.72s | 19.79s | −82.9% GPT-5.5 (High) is 82.9% faster |
| Price per 1M tokens (in / out) | $0.75 / $4.50 | $5.00 / $30.0 | |
| Input modalities | Text, Image | Text, Image |
GPT-5.5 (High) vs GPT-5.4 mini (Xhigh): 53.5% more intelligence, 123.8% more cost to run the AA benchmark, and 82.9% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-5.4 mini (Xhigh) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
- GPT-5.5 (High) is off the frontier: at the same or lower cost, Kimi K3.1 Pro scores 55.10 for $3117.
GPT-5.4 mini (Xhigh)GPT-5.5 (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-5-4-mini/gpt-5-5-high · Markdown: /api/v1/compare/gpt-5-4-mini/gpt-5-5-high?format=md · llms.txt · agent skill