Claude Sonnet 4.6 (Max) vs Gemini 3.5 Flash (High)
Which is better for the money: Claude Sonnet 4.6 (Max) by Anthropic or Gemini 3.5 Flash (High) by Google? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Clear winner
Verdict
Pick Gemini 3.5 Flash (High)
Gemini 3.5 Flash (High) vs Claude Sonnet 4.6 (Max): 8.3% more intelligence, 14.3% less cost to run the AA benchmark, and 84.2% faster end-to-end.
| Metric | Claude Sonnet 4.6 (Max) | Gemini 3.5 Flash (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 30.1 | 32.6 | +8.3% Gemini 3.5 Flash (Hig… is 8.3% more intelligent |
| Total AA cost (lower is better) | $4,924.80 | $4,222.12 | −14.3% Gemini 3.5 Flash (Hig… is 14.3% cheaper |
| End-to-end time (lower is better) | 104.36s | 16.54s | −84.2% Gemini 3.5 Flash (Hig… is 84.2% faster |
| Price per 1M tokens (in / out) | $3.00 / $15.0 | $1.50 / $9.00 | |
| Input modalities | Text, Image | Text, Image, Speech, Video |
Today's Pareto frontier
Against the frontier
- Claude Sonnet 4.6 (Max) is off the frontier: at the same or lower cost, Claude Opus 5.5 (Xhigh, Default Fallback) scores 56.00 for $4057.
- Gemini 3.5 Flash (High) is off the frontier: at the same or lower cost, Claude Opus 5.5 (Xhigh, Default Fallback) scores 56.00 for $4057.
Claude Sonnet 4.6 (Max)Gemini 3.5 Flash (High)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-4-6-adaptive/gemini-3-5-flash · Markdown: /api/v1/compare/claude-sonnet-4-6-adaptive/gemini-3-5-flash?format=md · llms.txt · agent skill