Claude Sonnet 5 (Medium) vs Gemini 3.6 Flash (High)
Which is better for the money: Claude Sonnet 5 (Medium) by Anthropic or Gemini 3.6 Flash (High) 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
Gemini 3.6 Flash (High) scores 5.9 points higher (34.0 vs 28.1) but costs 1.3× as much to run the benchmark ($1614 vs $1218; both premium class). Pick Gemini 3.6 Flash (High) when the extra intelligence is worth the premium, otherwise Claude Sonnet 5 (Medium).
| Metric | Claude Sonnet 5 (Medium) | Gemini 3.6 Flash (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 28.1 | 34.0 | +21.0% Gemini 3.6 Flash (Hig… is 21.0% more intelligent |
| Total AA cost (lower is better) | $1,218.17 | $1,614.42 | +32.5% Gemini 3.6 Flash (Hig… is 32.5% more expensive |
| End-to-end time (lower is better) | 8.58s | 17.59s | +105.0% Gemini 3.6 Flash (Hig… is 105.0% slower |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $0.75 / $3.75 | |
| Input modalities | Text, Image | Text, Image, Speech, Video |
Gemini 3.6 Flash (High) vs Claude Sonnet 5 (Medium): 21.0% more intelligence, 32.5% more cost to run the AA benchmark, and 105.0% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Sonnet 5 (Medium) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
- Gemini 3.6 Flash (High) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Claude Sonnet 5 (Medium)Gemini 3.6 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-5-medium/gemini-3-6-flash · Markdown: /api/v1/compare/claude-sonnet-5-medium/gemini-3-6-flash?format=md · llms.txt · agent skill