Celeris-1 vs GPT-5 mini (High)
Which is better for the money: Celeris-1 by Celeris or GPT-5 mini (High) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
GPT-5 mini (High) scores 10.5 points higher (16.8 vs 6.3) but costs 3.1× as much to run the benchmark ($189 vs $60.0; both mid-range class). They are not alternatives at one budget: pick GPT-5 mini (High) when you need intelligence above 6.3, and Celeris-1 when 6.3 is enough.
| Metric | Celeris-1 | GPT-5 mini (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.3 | 16.8 | +166.7% GPT-5 mini (High) is 2.7× more intelligent |
| Total AA cost (lower is better) | $59.99 | $188.66 | +214.5% GPT-5 mini (High) is 3.1× more expensive |
| End-to-end time (lower is better) | 0.87s | 58.72s | +6649.4% GPT-5 mini (High) is 6649.4% slower |
| Price per 1M tokens (in / out) | $0.20 / $0.70 | $0.25 / $2.00 | |
| Input modalities | Text, Image | Text, Image |
GPT-5 mini (High) vs Celeris-1: 166.7% more intelligence, 214.5% more cost to run the AA benchmark, and 6649.4% 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.
- GPT-5 mini (High) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Xhigh) scores 41.20 for $158.
Celeris-1GPT-5 mini (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/gpt-5-mini · Markdown: /api/v1/compare/celeris-1/gpt-5-mini?format=md · llms.txt · agent skill