Celeris-1 vs MiMo-V2.5
Which is better for the money: Celeris-1 by Celeris 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 15.5 points higher (21.8 vs 6.3) but costs 1.0× as much to run the benchmark ($61.9 vs $60.0; both mid-range class). Pick MiMo-V2.5 when the extra intelligence is worth the premium, otherwise Celeris-1.
| Metric | Celeris-1 | MiMo-V2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.3 | 21.8 | +246.0% MiMo-V2.5 is 3.5× more intelligent |
| Total AA cost (lower is better) | $59.99 | $61.93 | +3.2% MiMo-V2.5 is 3.2% more expensive |
| End-to-end time (lower is better) | 0.87s | 41.73s | +4696.6% MiMo-V2.5 is 4696.6% slower |
| Price per 1M tokens (in / out) | $0.20 / $0.70 | $0.13 / $0.27 | |
| Input modalities | Text, Image | Text, Image |
MiMo-V2.5 vs Celeris-1: 246.0% more intelligence, 3.2% more cost to run the AA benchmark, and 4696.6% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Celeris-1 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Medium) scores 34.50 for $56.4.
- MiMo-V2.5 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Medium) scores 34.50 for $56.4.
Celeris-1MiMo-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/celeris-1/mimo-v2-5-0424 · Markdown: /api/v1/compare/celeris-1/mimo-v2-5-0424?format=md · llms.txt · agent skill