Celeris-1 vs Inkling (xhigh)
Which is better for the money: Celeris-1 by Celeris or Inkling (xhigh) by Thinking Machines? 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
Inkling (xhigh) scores 19.2 points higher (25.5 vs 6.3) but costs 17× as much to run the benchmark ($1026 vs $60.0; premium vs mid-range cost classes). They are not alternatives at one budget: pick Inkling (xhigh) when you need intelligence above 6.3, and Celeris-1 when 6.3 is enough.
| Metric | Celeris-1 | Inkling (xhigh) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.3 | 25.5 | +304.8% Inkling (xhigh) is 4.0× more intelligent |
| Total AA cost (lower is better) | $59.99 | $1,026.14 | +1610.5% Inkling (xhigh) is 17× more expensive |
| End-to-end time (lower is better) | 0.97s | 37.45s | +3760.8% Inkling (xhigh) is 3760.8% slower |
| Price per 1M tokens (in / out) | $0.20 / $0.70 | $1.00 / $4.05 | |
| Input modalities | Not reported | Not reported |
Inkling (xhigh) vs Celeris-1: 304.8% more intelligence, 1610.5% more cost to run the AA benchmark, and 3760.8% 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.
- Inkling (xhigh) is off the frontier: at the same or lower cost, GLM-5.3-Flash scores 41.90 for $280.
Celeris-1Inkling (xhigh)Today'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/inkling · Markdown: /api/v1/compare/celeris-1/inkling?format=md · llms.txt · agent skill