GPT-5.5 (Xhigh) vs Mercury 2
Which is better for the money: GPT-5.5 (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-5.5 (Xhigh) scores 27.6 points higher (38.4 vs 10.8) but costs 50× as much to run the benchmark ($5294 vs $105; flagship vs mid-range cost classes). They are not alternatives at one budget: pick GPT-5.5 (Xhigh) when you need intelligence above 10.8, and Mercury 2 when 10.8 is enough.
| Metric | GPT-5.5 (Xhigh) | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 38.4 | 10.8 | −71.9% Mercury 2 is 71.9% less intelligent |
| Total AA cost (lower is better) | $5,294.36 | $104.94 | −98.0% Mercury 2 is 98.0% cheaper |
| End-to-end time (lower is better) | 44.96s | 8.08s | −82.0% Mercury 2 is 82.0% faster |
| Price per 1M tokens (in / out) | $5.00 / $30.0 | $0.25 / $0.75 | |
| Input modalities | Text, Image | Text |
Mercury 2 vs GPT-5.5 (Xhigh): 71.9% less intelligence, 98.0% less cost to run the AA benchmark, and 82.0% faster end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-5.5 (Xhigh) is off the frontier: at the same or lower cost, Claude Opus 5.5 (Xhigh, Default Fallback) scores 56.00 for $4057.
- Mercury 2 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 37.80 for $94.1.
GPT-5.5 (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-5-5/mercury-2 · Markdown: /api/v1/compare/gpt-5-5/mercury-2?format=md · llms.txt · agent skill