Claude Sonnet 5 (Xhigh) vs Mercury 2
Which is better for the money: Claude Sonnet 5 (Xhigh) by Anthropic 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
Claude Sonnet 5 (Xhigh) scores 23.6 points higher (34.4 vs 10.8) but costs 31× as much to run the benchmark ($3255 vs $105; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Claude Sonnet 5 (Xhigh) when you need intelligence above 10.8, and Mercury 2 when 10.8 is enough.
| Metric | Claude Sonnet 5 (Xhigh) | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 34.4 | 10.8 | −68.6% Mercury 2 is 68.6% less intelligent |
| Total AA cost (lower is better) | $3,255.40 | $104.94 | −96.8% Mercury 2 is 96.8% cheaper |
| End-to-end time (lower is better) | 26.92s | 6.56s | −75.6% Mercury 2 is 75.6% faster |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $0.25 / $0.75 | |
| Input modalities | Text, Image | Text |
Mercury 2 vs Claude Sonnet 5 (Xhigh): 68.6% less intelligence, 96.8% less cost to run the AA benchmark, and 75.6% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Sonnet 5 (Xhigh) is off the frontier: at the same or lower cost, Kimi K3.1 Pro scores 55.10 for $3117.
- Mercury 2 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 37.80 for $94.1.
Claude Sonnet 5 (Xhigh)Mercury 2Today'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-xhigh/mercury-2 · Markdown: /api/v1/compare/claude-sonnet-5-xhigh/mercury-2?format=md · llms.txt · agent skill