Gemini 2.5 Pro vs Gemini 3.1 Pro Preview
Which is better for the money: Gemini 2.5 Pro by Google 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 13.6 points higher (29.7 vs 16.1) but costs 2.4× as much to run the benchmark ($1935 vs $823; both premium class). Pick Gemini 3.1 Pro Preview when the extra intelligence is worth the premium, otherwise Gemini 2.5 Pro.
| Metric | Gemini 2.5 Pro | Gemini 3.1 Pro Preview | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 16.1 | 29.7 | +84.5% Gemini 3.1 Pro Preview is 84.5% more intelligent |
| Total AA cost (lower is better) | $822.85 | $1,935.39 | +135.2% Gemini 3.1 Pro Preview is 2.4× more expensive |
| End-to-end time (lower is better) | 27.19s | 24.32s | −10.6% Gemini 3.1 Pro Preview is 10.6% faster |
| Price per 1M tokens (in / out) | $1.25 / $10.0 | $2.00 / $12.0 | |
| Input modalities | Text, Image, Speech, Video | Text, Image, Speech, Video |
Gemini 3.1 Pro Preview vs Gemini 2.5 Pro: 84.5% more intelligence, 135.2% more cost to run the AA benchmark, and 10.6% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Gemini 2.5 Pro is off the frontier: at the same or lower cost, GPT-6.1 Sol (Xhigh) scores 51.00 for $662.
- 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.
Gemini 2.5 ProGemini 3.1 Pro PreviewToday's Pareto frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/gemini-2-5-pro/gemini-3-1-pro-preview · Markdown: /api/v1/compare/gemini-2-5-pro/gemini-3-1-pro-preview?format=md · llms.txt · agent skill