Gemini 3.5 Flash-Lite vs Mercury 2
Which is better for the money: Gemini 3.5 Flash-Lite 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 3.5 Flash-Lite scores 11.4 points higher (22.2 vs 10.8) but costs 3.5× as much to run the benchmark ($366 vs $105; both mid-range class). They are not alternatives at one budget: pick Gemini 3.5 Flash-Lite when you need intelligence above 10.8, and Mercury 2 when 10.8 is enough.
| Metric | Gemini 3.5 Flash-Lite | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 22.2 | 10.8 | −51.4% Mercury 2 is 51.4% less intelligent |
| Total AA cost (lower is better) | $365.63 | $104.94 | −71.3% Mercury 2 is 71.3% cheaper |
| End-to-end time (lower is better) | 8.50s | 6.65s | −21.8% Mercury 2 is 21.8% faster |
| Price per 1M tokens (in / out) | $0.30 / $2.50 | $0.25 / $0.75 | |
| Input modalities | Text, Image, Speech, Video | Text |
Mercury 2 vs Gemini 3.5 Flash-Lite: 51.4% less intelligence, 71.3% less cost to run the AA benchmark, and 21.8% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Gemini 3.5 Flash-Lite is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
- Mercury 2 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 37.80 for $94.1.
Gemini 3.5 Flash-LiteMercury 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-3-5-flash-lite/mercury-2 · Markdown: /api/v1/compare/gemini-3-5-flash-lite/mercury-2?format=md · llms.txt · agent skill