Gemini 3.1 Pro Preview vs Mercury 2.5
Which is better for the money: Gemini 3.1 Pro Preview by Google or Mercury 2.5 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 17.4 points higher (29.7 vs 12.3) but costs 8.9× as much to run the benchmark ($1935 vs $218; premium vs mid-range cost classes). They are not alternatives at one budget: pick Gemini 3.1 Pro Preview when you need intelligence above 12.3, and Mercury 2.5 when 12.3 is enough.
| Metric | Gemini 3.1 Pro Preview | Mercury 2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 29.7 | 12.3 | −58.6% Mercury 2.5 is 58.6% less intelligent |
| Total AA cost (lower is better) | $1,935.39 | $218.11 | −88.7% Mercury 2.5 is 88.7% cheaper |
| End-to-end time (lower is better) | 24.47s | 4.24s | −82.7% Mercury 2.5 is 82.7% faster |
| Price per 1M tokens (in / out) | $2.00 / $12.0 | $0.25 / $0.75 | |
| Input modalities | Text, Image, Speech, Video | Text |
Mercury 2.5 vs Gemini 3.1 Pro Preview: 58.6% less intelligence, 88.7% less cost to run the AA benchmark, and 82.7% 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 2.5 is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
Gemini 3.1 Pro PreviewMercury 2.5Today'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-2-5 · Markdown: /api/v1/compare/gemini-3-1-pro-preview/mercury-2-5?format=md · llms.txt · agent skill