Celeris-1 vs Claude Haiku 5.5 (High)
Which is better for the money: Celeris-1 by Celeris or Claude Haiku 5.5 (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 Haiku 5.5 (High) scores 31.5 points higher (37.8 vs 6.3) but costs 1.6× as much to run the benchmark ($94.1 vs $60.0; both mid-range class). Pick Claude Haiku 5.5 (High) when the extra intelligence is worth the premium, otherwise Celeris-1.
| Metric | Celeris-1 | Claude Haiku 5.5 (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.3 | 37.8 | +500.0% Claude Haiku 5.5 (Hig… is 6.0× more intelligent |
| Total AA cost (lower is better) | $59.99 | $94.07 | +56.8% Claude Haiku 5.5 (Hig… is 56.8% more expensive |
| End-to-end time (lower is better) | 0.87s | 25.67s | +2850.6% Claude Haiku 5.5 (Hig… is 2850.6% slower |
| Price per 1M tokens (in / out) | $0.20 / $0.70 | $0.10 / $0.50 | |
| Input modalities | Text, Image | Text, Image |
Claude Haiku 5.5 (High) vs Celeris-1: 500.0% more intelligence, 56.8% more cost to run the AA benchmark, and 2850.6% 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.
- Claude Haiku 5.5 (High) is on today's frontier: nothing is both smarter and cheaper.
Celeris-1Claude Haiku 5.5 (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-haiku-5-5-high · Markdown: /api/v1/compare/celeris-1/claude-haiku-5-5-high?format=md · llms.txt · agent skill