Gemini 3.1 Pro Preview vs Mercury 2
Which is better for the money: Gemini 3.1 Pro Preview by Google or Mercury 2 by Inception? 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
Gemini 3.1 Pro Preview scores 18.9 points higher (29.7 vs 10.8) but costs 18× as much to run the benchmark ($1935 vs $105; premium vs mid-range cost classes). They are not alternatives at one budget: pick Gemini 3.1 Pro Preview when you need intelligence above 10.8, and Mercury 2 when 10.8 is enough.
| Metric | Gemini 3.1 Pro Preview | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 29.7 | 10.8 | −63.6% Mercury 2 is 63.6% less intelligent |
| Total AA cost (lower is better) | $1,935.39 | $104.94 | −94.6% Mercury 2 is 94.6% cheaper |
| End-to-end time (lower is better) | 24.21s | 6.65s | −72.5% Mercury 2 is 72.5% faster |
| Price per 1M tokens (in / out) | $2.00 / $12.0 | $0.25 / $0.75 | |
| Input modalities | Text, Image, Speech, Video | Text |
Mercury 2 vs Gemini 3.1 Pro Preview: 63.6% less intelligence, 94.6% less cost to run the AA benchmark, and 72.5% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Gemini 3.1 Pro Preview is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
- Mercury 2 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 37.80 for $94.1.
Gemini 3.1 Pro PreviewMercury 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/gemini-3-1-pro-preview/mercury-2 · Markdown: /api/v1/compare/gemini-3-1-pro-preview/mercury-2?format=md · llms.txt · agent skill