GPT-5.4 nano (Xhigh) vs Mistral Large 3
Which is better for the money: GPT-5.4 nano (Xhigh) by OpenAI or Mistral Large 3 by Mistral? 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-5.4 nano (Xhigh) scores 11.4 points higher (20.7 vs 9.3) but costs 7.1× as much to run the benchmark ($331 vs $46.4; mid-range vs budget cost classes). They are not alternatives at one budget: pick GPT-5.4 nano (Xhigh) when you need intelligence above 9.3, and Mistral Large 3 when 9.3 is enough.
| Metric | GPT-5.4 nano (Xhigh) | Mistral Large 3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 20.7 | 9.3 | −55.1% Mistral Large 3 is 55.1% less intelligent |
| Total AA cost (lower is better) | $331.24 | $46.41 | −86.0% Mistral Large 3 is 86.0% cheaper |
| End-to-end time (lower is better) | 53.29s | 7.18s | −86.5% Mistral Large 3 is 86.5% faster |
| Price per 1M tokens (in / out) | $0.20 / $1.25 | $0.50 / $1.50 | |
| Input modalities | Text, Image | Text, Image |
Mistral Large 3 vs GPT-5.4 nano (Xhigh): 55.1% less intelligence, 86.0% less cost to run the AA benchmark, and 86.5% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-5.4 nano (Xhigh) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- Mistral Large 3 is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
GPT-5.4 nano (Xhigh)Mistral Large 3Today'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/gpt-5-4-nano/mistral-large-3 · Markdown: /api/v1/compare/gpt-5-4-nano/mistral-large-3?format=md · llms.txt · agent skill