Llama 4 Scout vs Mercury 2
Which is better for the money: Llama 4 Scout 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 4.3 points higher (10.8 vs 6.5) but costs 1.4× as much to run the benchmark ($105 vs $73.6; both mid-range class). Pick Mercury 2 when the extra intelligence is worth the premium, otherwise Llama 4 Scout.
| Metric | Llama 4 Scout | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.5 | 10.8 | +66.2% Mercury 2 is 66.2% more intelligent |
| Total AA cost (lower is better) | $73.56 | $104.94 | +42.7% Mercury 2 is 42.7% more expensive |
| End-to-end time (lower is better) | 5.00s | 6.65s | +33.0% Mercury 2 is 33.0% slower |
| Price per 1M tokens (in / out) | $0.18 / $0.66 | $0.25 / $0.75 | |
| Input modalities | Text, Image | Text |
Mercury 2 vs Llama 4 Scout: 66.2% more intelligence, 42.7% more cost to run the AA benchmark, and 33.0% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Llama 4 Scout is off the frontier: at the same or lower cost, GPT-6 Luna (Xhigh) scores 34.60 for $66.8.
- 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 ScoutMercury 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-scout/mercury-2 · Markdown: /api/v1/compare/llama-4-scout/mercury-2?format=md · llms.txt · agent skill