DeepSeek V3 (Dec '24) vs Gemini 3.8 Flash (Medium)
Which is better for the money: DeepSeek V3 (Dec '24) 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 31.3 points higher (39.8 vs 8.5) but costs 43× as much to run the benchmark ($1100 vs $25.4; premium vs budget cost classes). They are not alternatives at one budget: pick Gemini 3.8 Flash (Medium) when you need intelligence above 8.5, and DeepSeek V3 (Dec '24) when 8.5 is enough.
| Metric | DeepSeek V3 (Dec '24) | Gemini 3.8 Flash (Medium) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 8.5 | 39.8 | +368.2% Gemini 3.8 Flash (Med… is 4.7× more intelligent |
| Total AA cost (lower is better) | $25.37 | $1,100.06 | +4236.1% Gemini 3.8 Flash (Med… is 43× more expensive |
| End-to-end time (lower is better) | 11.84s | Not reported | — not comparable |
| Price per 1M tokens (in / out) | $0.32 / $0.89 | $0.75 / $3.75 | |
| Input modalities | Text | Text, Image, Speech, Video |
Gemini 3.8 Flash (Medium) vs DeepSeek V3 (Dec '24): 368.2% more intelligence, 4236.1% more cost to run the AA benchmark, and end-to-end time not fully reported.
Today's Pareto frontier
Against the frontier
- DeepSeek V3 (Dec '24) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- 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 V3 (Dec '24)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-v3/gemini-3-8-flash-medium · Markdown: /api/v1/compare/deepseek-v3/gemini-3-8-flash-medium?format=md · llms.txt · agent skill