Claude Sonnet 5 (High) vs Gemini 2.5 Pro
Which is better for the money: Claude Sonnet 5 (High) 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 (High) scores 15.6 points higher (31.7 vs 16.1) but costs 2.5× as much to run the benchmark ($2086 vs $823; flagship vs premium cost classes). Pick Claude Sonnet 5 (High) when the extra intelligence is worth the premium, otherwise Gemini 2.5 Pro.
| Metric | Claude Sonnet 5 (High) | Gemini 2.5 Pro | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 31.7 | 16.1 | −49.2% Gemini 2.5 Pro is 49.2% less intelligent |
| Total AA cost (lower is better) | $2,086.04 | $822.85 | −60.6% Gemini 2.5 Pro is 60.6% cheaper |
| End-to-end time (lower is better) | 15.23s | 27.19s | +78.5% Gemini 2.5 Pro is 78.5% 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 (High): 49.2% less intelligence, 60.6% less cost to run the AA benchmark, and 78.5% 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.
- 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 (High)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-high/gemini-2-5-pro · Markdown: /api/v1/compare/claude-sonnet-5-high/gemini-2-5-pro?format=md · llms.txt · agent skill