Claude Opus 5 (Max) vs Hy3
Which is better for the money: Claude Opus 5 (Max) by Anthropic or Hy3 by Tencent? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
Claude Opus 5 (Max) scores 25.5 points higher (50.8 vs 25.3) but costs 49× as much to run the benchmark ($7275 vs $150; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Claude Opus 5 (Max) when you need intelligence above 25.3, and Hy3 when 25.3 is enough.
| Metric | Claude Opus 5 (Max) | Hy3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 50.8 | 25.3 | −50.2% Hy3 is 50.2% less intelligent |
| Total AA cost (lower is better) | $7,274.74 | $149.61 | −97.9% Hy3 is 97.9% cheaper |
| End-to-end time (lower is better) | 59.61s | 33.73s | −43.4% Hy3 is 43.4% faster |
| Price per 1M tokens (in / out) | $5.00 / $25.0 | $0.14 / $0.56 | |
| Input modalities | Text, Image | Text |
Hy3 vs Claude Opus 5 (Max): 50.2% less intelligence, 97.9% less cost to run the AA benchmark, and 43.4% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Opus 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 Opus 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-opus-5/hy3 · Markdown: /api/v1/compare/claude-opus-5/hy3?format=md · llms.txt · agent skill