Granite 4.2 8B vs MiMo-V2.5
Which is better for the money: Granite 4.2 8B by IBM 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
MiMo-V2.5 scores 10.7 points higher (21.8 vs 11.1) but costs 1.2× as much to run the benchmark ($61.9 vs $53.1; both mid-range class). Pick MiMo-V2.5 when the extra intelligence is worth the premium, otherwise Granite 4.2 8B.
| Metric | Granite 4.2 8B | MiMo-V2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.1 | 21.8 | +96.4% MiMo-V2.5 is 96.4% more intelligent |
| Total AA cost (lower is better) | $53.07 | $61.93 | +16.7% MiMo-V2.5 is 16.7% more expensive |
| End-to-end time (lower is better) | 39.25s | 41.73s | +6.3% MiMo-V2.5 is 6.3% slower |
| Price per 1M tokens (in / out) | $0.06 / $0.25 | $0.13 / $0.27 | |
| Input modalities | Text | Text, Image |
MiMo-V2.5 vs Granite 4.2 8B: 96.4% more intelligence, 16.7% more cost to run the AA benchmark, and 6.3% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Granite 4.2 8B is off the frontier: at the same or lower cost, GPT-6 Luna (High) scores 32.90 for $47.9.
- MiMo-V2.5 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Medium) scores 34.50 for $56.4.
Granite 4.2 8BMiMo-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/granite-4-2-8b/mimo-v2-5-0424 · Markdown: /api/v1/compare/granite-4-2-8b/mimo-v2-5-0424?format=md · llms.txt · agent skill