Celeris-1 vs Mercury 2
Which is better for the money: Celeris-1 by Celeris or Mercury 2 by Inception? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-09-09.
Trade-off
Verdict
Depends on your budget
Mercury 2 scores 5.2 points higher (11.5 vs 6.3) but costs 2.5× as much to run the benchmark ($153 vs $60.0; both mid-range class). Pick Mercury 2 when the extra intelligence is worth the premium, otherwise Celeris-1.
| Metric | Celeris-1 | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.3 | 11.5 | +82.5% Mercury 2 is 82.5% more intelligent |
| Total AA cost (lower is better) | $59.99 | $152.55 | +154.3% Mercury 2 is 2.5× more expensive |
| End-to-end time (lower is better) | 0.97s | 4.57s | +371.1% Mercury 2 is 371.1% slower |
| Price per 1M tokens (in / out) | $0.20 / $0.70 | $0.25 / $0.75 | |
| Input modalities | Not reported | Not reported |
Mercury 2 vs Celeris-1: 82.5% more intelligence, 154.3% more cost to run the AA benchmark, and 371.1% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Celeris-1 is off the frontier: at the same or lower cost, MiMo-V2.5 scores 22.30 for $42.6.
- Mercury 2 is off the frontier: at the same or lower cost, MiMo-V2.5-Pro scores 26.40 for $138.
Celeris-1Mercury 2Today's Pareto 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/mercury-2 · Markdown: /api/v1/compare/celeris-1/mercury-2?format=md · llms.txt · agent skill