Claude Sonnet 5 (Xhigh) vs Gemini 2.5 Pro
Which is better for the money: Claude Sonnet 5 (Xhigh) by Anthropic or Gemini 2.5 Pro by Google? 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 18.3 points higher (34.4 vs 16.1) but costs 4.0× as much to run the benchmark ($3255 vs $823; flagship vs premium cost classes). They are not alternatives at one budget: pick Claude Sonnet 5 (Xhigh) when you need intelligence above 16.1, and Gemini 2.5 Pro when 16.1 is enough.
| Metric | Claude Sonnet 5 (Xhigh) | Gemini 2.5 Pro | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 34.4 | 16.1 | −53.2% Gemini 2.5 Pro is 53.2% less intelligent |
| Total AA cost (lower is better) | $3,255.40 | $822.85 | −74.7% Gemini 2.5 Pro is 74.7% cheaper |
| End-to-end time (lower is better) | 26.92s | 27.94s | +3.8% Gemini 2.5 Pro is 3.8% slower |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $1.25 / $10.0 | |
| Input modalities | Text, Image | Text, Image, Speech, Video |
Gemini 2.5 Pro vs Claude Sonnet 5 (Xhigh): 53.2% less intelligence, 74.7% less cost to run the AA benchmark, and 3.8% slower 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.
- Gemini 2.5 Pro is off the frontier: at the same or lower cost, GPT-6.1 Sol (Xhigh) scores 51.00 for $662.
Claude Sonnet 5 (Xhigh)Gemini 2.5 ProToday'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/gemini-2-5-pro · Markdown: /api/v1/compare/claude-sonnet-5-xhigh/gemini-2-5-pro?format=md · llms.txt · agent skill