DeepSeek V4 Pro 0813 (Non-reasoning) vs Gemini 3.5 Flash (High)

Which is better for the money: DeepSeek V4 Pro 0813 (Non-reasoning) by DeepSeek 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.

Trade-off

DeepSeekDeepSeek V4 Pro 0813 (Non-reasoning)Off the frontier

Intelligence: 20.40
Total cost: $451

GoogleGemini 3.5 Flash (High)Off the frontier

Intelligence: 32.60
Total cost: $4222

Verdict

Depends on your budget

Gemini 3.5 Flash (High) scores 12.2 points higher (32.6 vs 20.4) but costs 9.4× as much to run the benchmark ($4222 vs $451; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Gemini 3.5 Flash (High) when you need intelligence above 20.4, and DeepSeek V4 Pro 0813 (Non-reasoning) when 20.4 is enough.

Metric	DeepSeek V4 Pro 0813 (Non-reasoning)	Gemini 3.5 Flash (High)	Difference
Intelligence (higher is better)	20.4	32.6	+59.8% Gemini 3.5 Flash (Hig… is 59.8% more intelligent
Total AA cost (lower is better)	$450.76	$4,222.12	+836.7% Gemini 3.5 Flash (Hig… is 9.4× more expensive
End-to-end time (lower is better)	6.84s	16.52s	+141.5% Gemini 3.5 Flash (Hig… is 141.5% slower
Price per 1M tokens (in / out)	$1.32 / $3.96	$1.50 / $9.00
Input modalities	Text	Text, Image, Speech, Video

Gemini 3.5 Flash (High) vs DeepSeek V4 Pro 0813 (Non-reasoning): 59.8% more intelligence, 836.7% more cost to run the AA benchmark, and 141.5% slower end-to-end.

Open this matchup in the interactive picker DeepSeek V4 Pro 0813 (Non-reasoning): what beats it Gemini 3.5 Flash (High): what beats it

Today's Pareto frontier

Against the frontier

DeepSeek V4 Pro 0813 (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
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.

DeepSeek V4 Pro 0813 (Non-reasoning)Gemini 3.5 Flash (High)Today's Pareto frontierOpen-weights frontierEvery other model

Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/deepseek-v4-pro-non-reasoning/gemini-3-5-flash · Markdown: /api/v1/compare/deepseek-v4-pro-non-reasoning/gemini-3-5-flash?format=md · llms.txt · agent skill