Claude Sonnet 5 (High) vs Claude Sonnet 5 (Medium)
Which is better for the money: Claude Sonnet 5 (High) by Anthropic or Claude Sonnet 5 (Medium) by Anthropic? 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
Claude Sonnet 5 (High) scores 3.6 points higher (31.7 vs 28.1) but costs 1.7× as much to run the benchmark ($2086 vs $1218; flagship vs premium cost classes). Pick Claude Sonnet 5 (High) when the extra intelligence is worth the premium, otherwise Claude Sonnet 5 (Medium).
| Metric | Claude Sonnet 5 (High) | Claude Sonnet 5 (Medium) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 31.7 | 28.1 | −11.4% Claude Sonnet 5 (Medi… is 11.4% less intelligent |
| Total AA cost (lower is better) | $2,086.04 | $1,218.17 | −41.6% Claude Sonnet 5 (Medi… is 41.6% cheaper |
| End-to-end time (lower is better) | 15.10s | 9.02s | −40.3% Claude Sonnet 5 (Medi… is 40.3% faster |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $2.00 / $10.0 | |
| Input modalities | Text, Image | Text, Image |
Claude Sonnet 5 (Medium) vs Claude Sonnet 5 (High): 11.4% less intelligence, 41.6% less cost to run the AA benchmark, and 40.3% 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.
- Claude Sonnet 5 (Medium) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Claude Sonnet 5 (High)Claude Sonnet 5 (Medium)Today'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/claude-sonnet-5-high/claude-sonnet-5-medium · Markdown: /api/v1/compare/claude-sonnet-5-high/claude-sonnet-5-medium?format=md · llms.txt · agent skill