DeepSeek V4 Pro 0813 (Non-reasoning) vs Gemini 3.8 Flash (Medium)
Which is better for the money: DeepSeek V4 Pro 0813 (Non-reasoning) by DeepSeek or Gemini 3.8 Flash (Medium) 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 3.8 Flash (Medium) scores 19.4 points higher (39.8 vs 20.4) but costs 2.4× as much to run the benchmark ($1100 vs $451; premium vs mid-range cost classes). Pick Gemini 3.8 Flash (Medium) when the extra intelligence is worth the premium, otherwise DeepSeek V4 Pro 0813 (Non-reasoning).
| Metric | DeepSeek V4 Pro 0813 (Non-reasoning) | Gemini 3.8 Flash (Medium) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 20.4 | 39.8 | +95.1% Gemini 3.8 Flash (Med… is 95.1% more intelligent |
| Total AA cost (lower is better) | $450.76 | $1,100.06 | +144.0% Gemini 3.8 Flash (Med… is 2.4× more expensive |
| End-to-end time (lower is better) | 6.74s | Not reported | — not comparable |
| Price per 1M tokens (in / out) | $1.32 / $3.96 | $0.75 / $3.75 | |
| Input modalities | Text | Text, Image, Speech, Video |
Gemini 3.8 Flash (Medium) vs DeepSeek V4 Pro 0813 (Non-reasoning): 95.1% more intelligence, 144.0% more cost to run the AA benchmark, and end-to-end time not fully reported.
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 3.8 Flash (Medium) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
DeepSeek V4 Pro 0813 (Non-reasoning)Gemini 3.8 Flash (Medium)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-3-8-flash-medium · Markdown: /api/v1/compare/deepseek-v4-pro-non-reasoning/gemini-3-8-flash-medium?format=md · llms.txt · agent skill