Celeris-1 vs Trinity Large Thinking
Which is better for the money: Celeris-1 by Celeris or Trinity Large Thinking by Arcee AI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-08-17.
Trade-off
Verdict
Depends on your budget
Trinity Large Thinking scores 6.3 points higher (18.7 vs 12.4) but costs 1.6× as much to run the benchmark ($255 vs $157; both mid-range class). Pick Trinity Large Thinking when the extra intelligence is worth the premium, otherwise Celeris-1.
| Metric | Celeris-1 | Trinity Large Thinking | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 12.4 | 18.7 | +50.8% Trinity Large Thinking is 50.8% more intelligent |
| Total AA cost (lower is better) | $156.79 | $254.72 | +62.5% Trinity Large Thinking is 62.5% more expensive |
| End-to-end time (lower is better) | 0.97s | 13.49s | +1290.7% Trinity Large Thinking is 1290.7% slower |
| Price per 1M tokens (in / out) | $0.20 / $0.70 | $0.23 / $0.88 | |
| Input modalities | Not reported | Not reported |
Trinity Large Thinking vs Celeris-1: 50.8% more intelligence, 62.5% more cost to run the AA benchmark, and 1290.7% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Celeris-1 is off the frontier: at the same or lower cost, GPT-5.6 Luna (xhigh) scores 50.10 for $95.1.
- Trinity Large Thinking is off the frontier: at the same or lower cost, GPT-5.6 Luna (max) scores 52.30 for $172.
Celeris-1Trinity Large ThinkingToday'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/trinity-large-thinking · Markdown: /api/v1/compare/celeris-1/trinity-large-thinking?format=md · llms.txt · agent skill