Claude Sonnet 5 (High) vs Llama 4 Maverick
Which is better for the money: Claude Sonnet 5 (High) by Anthropic or Llama 4 Maverick by Meta? 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
Claude Sonnet 5 (High) scores 22.4 points higher (31.7 vs 9.3) but costs 47× as much to run the benchmark ($2086 vs $44.0; flagship vs budget cost classes). They are not alternatives at one budget: pick Claude Sonnet 5 (High) when you need intelligence above 9.3, and Llama 4 Maverick when 9.3 is enough.
| Metric | Claude Sonnet 5 (High) | Llama 4 Maverick | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 31.7 | 9.3 | −70.7% Llama 4 Maverick is 70.7% less intelligent |
| Total AA cost (lower is better) | $2,086.04 | $43.98 | −97.9% Llama 4 Maverick is 97.9% cheaper |
| End-to-end time (lower is better) | 19.10s | 10.41s | −45.5% Llama 4 Maverick is 45.5% faster |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $0.25 / $0.92 | |
| Input modalities | Text, Image | Text, Image |
Llama 4 Maverick vs Claude Sonnet 5 (High): 70.7% less intelligence, 97.9% less cost to run the AA benchmark, and 45.5% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Sonnet 5 (High) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
- Llama 4 Maverick is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
Claude Sonnet 5 (High)Llama 4 MaverickToday'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/claude-sonnet-5-high/llama-4-maverick · Markdown: /api/v1/compare/claude-sonnet-5-high/llama-4-maverick?format=md · llms.txt · agent skill