Celeris-1 vs Beam 1.0
Which is better for the money: Celeris-1 by Celeris or Beam 1.0 by Reflection? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-17.
Trade-off
Verdict
Depends on your budget
Beam 1.0 scores 24.0 points higher (30.3 vs 6.3) but costs 12× as much to run the benchmark ($740 vs $60.0; premium vs mid-range cost classes). They are not alternatives at one budget: pick Beam 1.0 when you need intelligence above 6.3, and Celeris-1 when 6.3 is enough.
| Metric | Celeris-1 | Beam 1.0 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.3 | 30.3 | +381.0% Beam 1.0 is 4.8× more intelligent |
| Total AA cost (lower is better) | $59.99 | $739.78 | +1133.2% Beam 1.0 is 12× more expensive |
| End-to-end time (lower is better) | 0.91s | 13.31s | +1362.6% Beam 1.0 is 1362.6% slower |
| Price per 1M tokens (in / out) | $0.20 / $0.70 | $0.70 / $2.10 | |
| Input modalities | Text, Image | Text |
Beam 1.0 vs Celeris-1: 381.0% more intelligence, 1133.2% more cost to run the AA benchmark, and 1362.6% 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.
- Beam 1.0 is off the frontier: at the same or lower cost, GPT-6.1 Sol (Xhigh) scores 51.00 for $662.
Celeris-1Beam 1.0Today'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/reflection-beam · Markdown: /api/v1/compare/celeris-1/reflection-beam?format=md · llms.txt · agent skill