Claude Sonnet 5 (High) vs Claude Sonnet 5 (Xhigh)
Which is better for the money: Claude Sonnet 5 (High) by Anthropic or Claude Sonnet 5 (Xhigh) 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 (Xhigh) scores 2.7 points higher (34.4 vs 31.7) but costs 1.6× as much to run the benchmark ($3255 vs $2086; both flagship class). Pick Claude Sonnet 5 (Xhigh) when the extra intelligence is worth the premium, otherwise Claude Sonnet 5 (High).
| Metric | Claude Sonnet 5 (High) | Claude Sonnet 5 (Xhigh) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 31.7 | 34.4 | +8.5% Claude Sonnet 5 (Xhig… is 8.5% more intelligent |
| Total AA cost (lower is better) | $2,086.04 | $3,255.40 | +56.1% Claude Sonnet 5 (Xhig… is 56.1% more expensive |
| End-to-end time (lower is better) | 15.10s | 20.97s | +38.9% Claude Sonnet 5 (Xhig… is 38.9% slower |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $2.00 / $10.0 | |
| Input modalities | Text, Image | Text, Image |
Claude Sonnet 5 (Xhigh) vs Claude Sonnet 5 (High): 8.5% more intelligence, 56.1% more cost to run the AA benchmark, and 38.9% slower 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 (Xhigh) is off the frontier: at the same or lower cost, Kimi K3.1 Pro scores 55.10 for $3117.
Claude Sonnet 5 (High)Claude Sonnet 5 (Xhigh)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-xhigh · Markdown: /api/v1/compare/claude-sonnet-5-high/claude-sonnet-5-xhigh?format=md · llms.txt · agent skill