Gemma 4 E4B (Reasoning) vs Mercury 2.5
Which is better for the money: Gemma 4 E4B (Reasoning) by Google or Mercury 2.5 by Inception? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
Mercury 2.5 scores 3.4 points higher (12.3 vs 8.9) but costs 15× as much to run the benchmark ($218 vs $14.7; mid-range vs budget cost classes). They are not alternatives at one budget: pick Mercury 2.5 when you need intelligence above 8.9, and Gemma 4 E4B (Reasoning) when 8.9 is enough.
| Metric | Gemma 4 E4B (Reasoning) | Mercury 2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 8.9 | 12.3 | +38.2% Mercury 2.5 is 38.2% more intelligent |
| Total AA cost (lower is better) | $14.68 | $218.11 | +1385.8% Mercury 2.5 is 15× more expensive |
| End-to-end time (lower is better) | 57.75s | 4.39s | −92.4% Mercury 2.5 is 92.4% faster |
| Price per 1M tokens (in / out) | $0.02 / $0.10 | $0.25 / $0.75 | |
| Input modalities | Text, Image, Speech, Video | Text |
Mercury 2.5 vs Gemma 4 E4B (Reasoning): 38.2% more intelligence, 1385.8% more cost to run the AA benchmark, and 92.4% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Gemma 4 E4B (Reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- Mercury 2.5 is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
Gemma 4 E4B (Reasoning)Mercury 2.5Today's Pareto frontierOpen-weights frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/gemma-4-e4b/mercury-2-5 · Markdown: /api/v1/compare/gemma-4-e4b/mercury-2-5?format=md · llms.txt · agent skill