Hy3 vs MiMo-V2.5
Which is better for the money: Hy3 by Tencent or MiMo-V2.5 by Xiaomi? 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 3.5 points higher (25.3 vs 21.8) but costs 2.4× as much to run the benchmark ($150 vs $61.9; both mid-range class). Pick Hy3 when the extra intelligence is worth the premium, otherwise MiMo-V2.5.
| Metric | Hy3 | MiMo-V2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 25.3 | 21.8 | −13.8% MiMo-V2.5 is 13.8% less intelligent |
| Total AA cost (lower is better) | $149.61 | $61.93 | −58.6% MiMo-V2.5 is 58.6% cheaper |
| End-to-end time (lower is better) | 33.29s | 41.73s | +25.4% MiMo-V2.5 is 25.4% slower |
| Price per 1M tokens (in / out) | $0.14 / $0.56 | $0.13 / $0.27 | |
| Input modalities | Text | Text, Image |
MiMo-V2.5 vs Hy3: 13.8% less intelligence, 58.6% less cost to run the AA benchmark, and 25.4% slower 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.
- MiMo-V2.5 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Medium) scores 34.50 for $56.4.
Hy3MiMo-V2.5Today'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/mimo-v2-5-0424 · Markdown: /api/v1/compare/hy3/mimo-v2-5-0424?format=md · llms.txt · agent skill