Claude Sonnet 5 (Medium) vs Hy3
Which is better for the money: Claude Sonnet 5 (Medium) 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 (Medium) scores 2.8 points higher (28.1 vs 25.3) but costs 8.1× as much to run the benchmark ($1218 vs $150; premium vs mid-range cost classes). They are not alternatives at one budget: pick Claude Sonnet 5 (Medium) when you need intelligence above 25.3, and Hy3 when 25.3 is enough.
| Metric | Claude Sonnet 5 (Medium) | Hy3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 28.1 | 25.3 | −10.0% Hy3 is 10.0% less intelligent |
| Total AA cost (lower is better) | $1,218.17 | $149.61 | −87.7% Hy3 is 87.7% cheaper |
| End-to-end time (lower is better) | 9.02s | 33.29s | +269.1% Hy3 is 269.1% slower |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $0.14 / $0.56 | |
| Input modalities | Text, Image | Text |
Hy3 vs Claude Sonnet 5 (Medium): 10.0% less intelligence, 87.7% less cost to run the AA benchmark, and 269.1% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Sonnet 5 (Medium) 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.
Claude Sonnet 5 (Medium)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-medium/hy3 · Markdown: /api/v1/compare/claude-sonnet-5-medium/hy3?format=md · llms.txt · agent skill