GPT-5.4 nano (Xhigh) vs Mercury 2
Which is better for the money: GPT-5.4 nano (Xhigh) by OpenAI or Mercury 2 by Inception? 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 9.9 points higher (20.7 vs 10.8) but costs 3.2× as much to run the benchmark ($331 vs $105; both mid-range class). They are not alternatives at one budget: pick GPT-5.4 nano (Xhigh) when you need intelligence above 10.8, and Mercury 2 when 10.8 is enough.
| Metric | GPT-5.4 nano (Xhigh) | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 20.7 | 10.8 | −47.8% Mercury 2 is 47.8% less intelligent |
| Total AA cost (lower is better) | $331.24 | $104.94 | −68.3% Mercury 2 is 68.3% cheaper |
| End-to-end time (lower is better) | 53.29s | 8.08s | −84.8% Mercury 2 is 84.8% faster |
| Price per 1M tokens (in / out) | $0.20 / $1.25 | $0.25 / $0.75 | |
| Input modalities | Text, Image | Text |
Mercury 2 vs GPT-5.4 nano (Xhigh): 47.8% less intelligence, 68.3% less cost to run the AA benchmark, and 84.8% 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.
- Mercury 2 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 37.80 for $94.1.
GPT-5.4 nano (Xhigh)Mercury 2Today'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-nano/mercury-2 · Markdown: /api/v1/compare/gpt-5-4-nano/mercury-2?format=md · llms.txt · agent skill