DeepSeek R1 (Jan '25) vs Gemini 3.1 Pro Preview
Which is better for the money: DeepSeek R1 (Jan '25) by DeepSeek or Gemini 3.1 Pro Preview 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 3.1 Pro Preview scores 18.3 points higher (29.7 vs 11.4) but costs 4.2× as much to run the benchmark ($1935 vs $461; premium vs mid-range cost classes). They are not alternatives at one budget: pick Gemini 3.1 Pro Preview when you need intelligence above 11.4, and DeepSeek R1 (Jan '25) when 11.4 is enough.
| Metric | DeepSeek R1 (Jan '25) | Gemini 3.1 Pro Preview | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.4 | 29.7 | +160.5% Gemini 3.1 Pro Preview is 2.6× more intelligent |
| Total AA cost (lower is better) | $460.74 | $1,935.39 | +320.1% Gemini 3.1 Pro Preview is 4.2× more expensive |
| End-to-end time (lower is better) | 20.14s | 25.04s | +24.3% Gemini 3.1 Pro Preview is 24.3% slower |
| Price per 1M tokens (in / out) | $2.00 / $4.00 | $2.00 / $12.0 | |
| Input modalities | Text | Text, Image, Speech, Video |
Gemini 3.1 Pro Preview vs DeepSeek R1 (Jan '25): 160.5% more intelligence, 320.1% more cost to run the AA benchmark, and 24.3% slower end-to-end.
Today's Pareto frontier
Against the frontier
- DeepSeek R1 (Jan '25) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
- Gemini 3.1 Pro Preview is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
DeepSeek R1 (Jan '25)Gemini 3.1 Pro PreviewToday'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-r1-0120/gemini-3-1-pro-preview · Markdown: /api/v1/compare/deepseek-r1-0120/gemini-3-1-pro-preview?format=md · llms.txt · agent skill