DeepSeek V4.1 Flash (Non-reasoning) vs Hy3
Which is better for the money: DeepSeek V4.1 Flash (Non-reasoning) by DeepSeek or Hy3 by Tencent? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Clear winner
Verdict
Pick Hy3
Hy3 vs DeepSeek V4.1 Flash (Non-reasoning): 2.4% more intelligence, 37.4% less cost to run the AA benchmark, and 1145.5% slower end-to-end.
| Metric | DeepSeek V4.1 Flash (Non-reasoning) | Hy3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 24.7 | 25.3 | +2.4% Hy3 is 2.4% more intelligent |
| Total AA cost (lower is better) | $238.91 | $149.61 | −37.4% Hy3 is 37.4% cheaper |
| End-to-end time (lower is better) | 2.66s | 33.13s | +1145.5% Hy3 is 1145.5% slower |
| Price per 1M tokens (in / out) | $0.30 / $1.20 | $0.14 / $0.56 | |
| Input modalities | Text, Image | Text |
Today's Pareto frontier
Against the frontier
- DeepSeek V4.1 Flash (Non-reasoning) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- Hy3 is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
DeepSeek V4.1 Flash (Non-reasoning)Hy3Today'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-v4-1-flash-non-reasoning/hy3 · Markdown: /api/v1/compare/deepseek-v4-1-flash-non-reasoning/hy3?format=md · llms.txt · agent skill