Gemini 3.6 Flash (High) vs Mercury 2.5
Which is better for the money: Gemini 3.6 Flash (High) 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 3.6 Flash (High) scores 21.7 points higher (34.0 vs 12.3) but costs 7.4× as much to run the benchmark ($1614 vs $218; premium vs mid-range cost classes). They are not alternatives at one budget: pick Gemini 3.6 Flash (High) when you need intelligence above 12.3, and Mercury 2.5 when 12.3 is enough.
| Metric | Gemini 3.6 Flash (High) | Mercury 2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 34.0 | 12.3 | −63.8% Mercury 2.5 is 63.8% less intelligent |
| Total AA cost (lower is better) | $1,614.42 | $218.11 | −86.5% Mercury 2.5 is 86.5% cheaper |
| End-to-end time (lower is better) | 18.02s | 4.33s | −76.0% Mercury 2.5 is 76.0% faster |
| Price per 1M tokens (in / out) | $0.75 / $3.75 | $0.25 / $0.75 | |
| Input modalities | Text, Image, Speech, Video | Text |
Mercury 2.5 vs Gemini 3.6 Flash (High): 63.8% less intelligence, 86.5% less cost to run the AA benchmark, and 76.0% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Gemini 3.6 Flash (High) 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 3.6 Flash (High)Mercury 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-3-6-flash/mercury-2-5 · Markdown: /api/v1/compare/gemini-3-6-flash/mercury-2-5?format=md · llms.txt · agent skill