Hy3 vs Mercury 2
Which is better for the money: Hy3 by Tencent or Mercury 2 by Inception? 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
Hy3 scores 14.5 points higher (25.3 vs 10.8) but costs 1.4× as much to run the benchmark ($150 vs $105; both mid-range class). Pick Hy3 when the extra intelligence is worth the premium, otherwise Mercury 2.
| Metric | Hy3 | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 25.3 | 10.8 | −57.3% Mercury 2 is 57.3% less intelligent |
| Total AA cost (lower is better) | $149.61 | $104.94 | −29.9% Mercury 2 is 29.9% cheaper |
| End-to-end time (lower is better) | 33.29s | 8.08s | −75.7% Mercury 2 is 75.7% faster |
| Price per 1M tokens (in / out) | $0.14 / $0.56 | $0.25 / $0.75 | |
| Input modalities | Text | Text |
Mercury 2 vs Hy3: 57.3% less intelligence, 29.9% less cost to run the AA benchmark, and 75.7% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Hy3 is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
- Mercury 2 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 37.80 for $94.1.
Hy3Mercury 2Today'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/hy3/mercury-2 · Markdown: /api/v1/compare/hy3/mercury-2?format=md · llms.txt · agent skill