DeepSeek R1 (Jan '25) vs Gemini 2.5 Pro
Which is better for the money: DeepSeek R1 (Jan '25) by DeepSeek or Gemini 2.5 Pro 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 2.5 Pro scores 4.7 points higher (16.1 vs 11.4) but costs 1.8× as much to run the benchmark ($823 vs $461; premium vs mid-range cost classes). Pick Gemini 2.5 Pro when the extra intelligence is worth the premium, otherwise DeepSeek R1 (Jan '25).
| Metric | DeepSeek R1 (Jan '25) | Gemini 2.5 Pro | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.4 | 16.1 | +41.2% Gemini 2.5 Pro is 41.2% more intelligent |
| Total AA cost (lower is better) | $460.74 | $822.85 | +78.6% Gemini 2.5 Pro is 78.6% more expensive |
| End-to-end time (lower is better) | 20.16s | 27.19s | +34.9% Gemini 2.5 Pro is 34.9% slower |
| Price per 1M tokens (in / out) | $2.00 / $4.00 | $1.25 / $10.0 | |
| Input modalities | Text | Text, Image, Speech, Video |
Gemini 2.5 Pro vs DeepSeek R1 (Jan '25): 41.2% more intelligence, 78.6% more cost to run the AA benchmark, and 34.9% 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 2.5 Pro is off the frontier: at the same or lower cost, GPT-6.1 Sol (Xhigh) scores 51.00 for $662.
DeepSeek R1 (Jan '25)Gemini 2.5 ProToday'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-2-5-pro · Markdown: /api/v1/compare/deepseek-r1-0120/gemini-2-5-pro?format=md · llms.txt · agent skill