Celeris-1 vs Claude Sonnet 5 (High)
Which is better for the money: Celeris-1 by Celeris or Claude Sonnet 5 (High) by Anthropic? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
Claude Sonnet 5 (High) scores 25.4 points higher (31.7 vs 6.3) but costs 35× as much to run the benchmark ($2086 vs $60.0; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Claude Sonnet 5 (High) when you need intelligence above 6.3, and Celeris-1 when 6.3 is enough.
| Metric | Celeris-1 | Claude Sonnet 5 (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.3 | 31.7 | +403.2% Claude Sonnet 5 (High) is 5.0× more intelligent |
| Total AA cost (lower is better) | $59.99 | $2,086.04 | +3377.3% Claude Sonnet 5 (High) is 35× more expensive |
| End-to-end time (lower is better) | 0.87s | 14.79s | +1600.0% Claude Sonnet 5 (High) is 1600.0% slower |
| Price per 1M tokens (in / out) | $0.20 / $0.70 | $2.00 / $10.0 | |
| Input modalities | Text, Image | Text, Image |
Claude Sonnet 5 (High) vs Celeris-1: 403.2% more intelligence, 3377.3% more cost to run the AA benchmark, and 1600.0% 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.
- Claude Sonnet 5 (High) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Celeris-1Claude Sonnet 5 (High)Today'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/claude-sonnet-5-high · Markdown: /api/v1/compare/celeris-1/claude-sonnet-5-high?format=md · llms.txt · agent skill