gpt-oss-20b (High) vs Hy3
Which is better for the money: gpt-oss-20b (High) by OpenAI 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
Hy3 scores 16.3 points higher (25.3 vs 9.0) but costs 5.2× as much to run the benchmark ($150 vs $28.8; mid-range vs budget cost classes). They are not alternatives at one budget: pick Hy3 when you need intelligence above 9.0, and gpt-oss-20b (High) when 9.0 is enough.
| Metric | gpt-oss-20b (High) | Hy3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 9.0 | 25.3 | +181.1% Hy3 is 2.8× more intelligent |
| Total AA cost (lower is better) | $28.81 | $149.61 | +419.3% Hy3 is 5.2× more expensive |
| End-to-end time (lower is better) | 16.79s | 33.13s | +97.3% Hy3 is 97.3% slower |
| Price per 1M tokens (in / out) | $0.05 / $0.22 | $0.14 / $0.56 | |
| Input modalities | Text | Text |
Hy3 vs gpt-oss-20b (High): 181.1% more intelligence, 419.3% more cost to run the AA benchmark, and 97.3% slower end-to-end.
Today's Pareto frontier
Against the frontier
- gpt-oss-20b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- Hy3 is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
gpt-oss-20b (High)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/gpt-oss-20b/hy3 · Markdown: /api/v1/compare/gpt-oss-20b/hy3?format=md · llms.txt · agent skill