Celeris-1 vs Claude Haiku 5.5 (Max)
Which is better for the money: Celeris-1 by Celeris or Claude Haiku 5.5 (Max) 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 (Max) scores 37.1 points higher (43.4 vs 6.3) but costs 5.5× as much to run the benchmark ($330 vs $60.0; both mid-range class). They are not alternatives at one budget: pick Claude Haiku 5.5 (Max) when you need intelligence above 6.3, and Celeris-1 when 6.3 is enough.
| Metric | Celeris-1 | Claude Haiku 5.5 (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.3 | 43.4 | +588.9% Claude Haiku 5.5 (Max) is 6.9× more intelligent |
| Total AA cost (lower is better) | $59.99 | $330.25 | +450.5% Claude Haiku 5.5 (Max) is 5.5× more expensive |
| End-to-end time (lower is better) | 0.87s | 318.48s | +36506.9% Claude Haiku 5.5 (Max) is 36506.9% 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 (Max) vs Celeris-1: 588.9% more intelligence, 450.5% more cost to run the AA benchmark, and 36506.9% 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 (Max) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
Celeris-1Claude Haiku 5.5 (Max)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 · Markdown: /api/v1/compare/celeris-1/claude-haiku-5-5?format=md · llms.txt · agent skill