Claude Fable 5.1 (Medium, Default Fallback) vs Hy3
Which is better for the money: Claude Fable 5.1 (Medium, Default Fallback) 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 Fable 5.1 (Medium, Default Fallb… scores 23.6 points higher (48.9 vs 25.3) but costs 27× as much to run the benchmark ($3983 vs $150; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Claude Fable 5.1 (Medium, Default Fallb… when you need intelligence above 25.3, and Hy3 when 25.3 is enough.
| Metric | Claude Fable 5.1 (Medium, Default Fallback) | Hy3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 48.9 | 25.3 | −48.3% Hy3 is 48.3% less intelligent |
| Total AA cost (lower is better) | $3,983.28 | $149.61 | −96.2% Hy3 is 96.2% cheaper |
| End-to-end time (lower is better) | 13.26s | 33.13s | +149.8% Hy3 is 149.8% slower |
| Price per 1M tokens (in / out) | $10.0 / $50.0 | $0.14 / $0.56 | |
| Input modalities | Text, Image | Text |
Hy3 vs Claude Fable 5.1 (Medium, Default Fallback): 48.3% less intelligence, 96.2% less cost to run the AA benchmark, and 149.8% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Fable 5.1 (Medium, Default Fallback) is off the frontier: at the same or lower cost, Kimi K3.1 Pro scores 55.10 for $3117.
- Hy3 is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
Claude Fable 5.1 (Medium, Default Fallback)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-fable-5-1-medium/hy3 · Markdown: /api/v1/compare/claude-fable-5-1-medium/hy3?format=md · llms.txt · agent skill