Gemini 3.1 Pro Preview vs Hy3
Which is better for the money: Gemini 3.1 Pro Preview by Google or Hy3 by Tencent? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
Gemini 3.1 Pro Preview scores 4.4 points higher (29.7 vs 25.3) but costs 13× as much to run the benchmark ($1935 vs $150; premium vs mid-range cost classes). They are not alternatives at one budget: pick Gemini 3.1 Pro Preview when you need intelligence above 25.3, and Hy3 when 25.3 is enough.
| Metric | Gemini 3.1 Pro Preview | Hy3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 29.7 | 25.3 | −14.8% Hy3 is 14.8% less intelligent |
| Total AA cost (lower is better) | $1,935.39 | $149.61 | −92.3% Hy3 is 92.3% cheaper |
| End-to-end time (lower is better) | 24.90s | 33.29s | +33.7% Hy3 is 33.7% slower |
| Price per 1M tokens (in / out) | $2.00 / $12.0 | $0.14 / $0.56 | |
| Input modalities | Text, Image, Speech, Video | Text |
Hy3 vs Gemini 3.1 Pro Preview: 14.8% less intelligence, 92.3% less cost to run the AA benchmark, and 33.7% slower end-to-end.
Today's Pareto frontier
Against the frontier
- 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.
- Hy3 is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
Gemini 3.1 Pro PreviewHy3Today'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/gemini-3-1-pro-preview/hy3 · Markdown: /api/v1/compare/gemini-3-1-pro-preview/hy3?format=md · llms.txt · agent skill