Claude Sonnet 5 (Max) vs Hy3
Which is better for the money: Claude Sonnet 5 (Max) by Anthropic 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
Claude Sonnet 5 (Max) scores 12.9 points higher (38.2 vs 25.3) but costs 47× as much to run the benchmark ($6998 vs $150; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Claude Sonnet 5 (Max) when you need intelligence above 25.3, and Hy3 when 25.3 is enough.
| Metric | Claude Sonnet 5 (Max) | Hy3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 38.2 | 25.3 | −33.8% Hy3 is 33.8% less intelligent |
| Total AA cost (lower is better) | $6,998.25 | $149.61 | −97.9% Hy3 is 97.9% cheaper |
| End-to-end time (lower is better) | 183.62s | 33.29s | −81.9% Hy3 is 81.9% faster |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $0.14 / $0.56 | |
| Input modalities | Text, Image | Text |
Hy3 vs Claude Sonnet 5 (Max): 33.8% less intelligence, 97.9% less cost to run the AA benchmark, and 81.9% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Sonnet 5 (Max) is off the frontier: at the same or lower cost, Claude Opus 5.5 (Xhigh, Default Fallback) scores 56.00 for $4057.
- Hy3 is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
Claude Sonnet 5 (Max)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/claude-sonnet-5/hy3 · Markdown: /api/v1/compare/claude-sonnet-5/hy3?format=md · llms.txt · agent skill