Llama 4 Maverick vs Mercury 2
Which is better for the money: Llama 4 Maverick by Meta 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
Mercury 2 scores 1.5 points higher (10.8 vs 9.3) but costs 2.4× as much to run the benchmark ($105 vs $44.0; mid-range vs budget cost classes). Pick Mercury 2 when the extra intelligence is worth the premium, otherwise Llama 4 Maverick.
| Metric | Llama 4 Maverick | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 9.3 | 10.8 | +16.1% Mercury 2 is 16.1% more intelligent |
| Total AA cost (lower is better) | $43.98 | $104.94 | +138.6% Mercury 2 is 2.4× more expensive |
| End-to-end time (lower is better) | 10.45s | 6.56s | −37.2% Mercury 2 is 37.2% faster |
| Price per 1M tokens (in / out) | $0.25 / $0.92 | $0.25 / $0.75 | |
| Input modalities | Text, Image | Text |
Mercury 2 vs Llama 4 Maverick: 16.1% more intelligence, 138.6% more cost to run the AA benchmark, and 37.2% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Llama 4 Maverick is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
- Mercury 2 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 37.80 for $94.1.
Llama 4 MaverickMercury 2Today'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/llama-4-maverick/mercury-2 · Markdown: /api/v1/compare/llama-4-maverick/mercury-2?format=md · llms.txt · agent skill