Celeris-1 vs Grok 4.6 (Medium)
Which is better for the money: Celeris-1 by Celeris or Grok 4.6 (Medium) by SpaceXAI? 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
Grok 4.6 (Medium) scores 36.5 points higher (42.8 vs 6.3) but costs 26× as much to run the benchmark ($1557 vs $60.0; premium vs mid-range cost classes). They are not alternatives at one budget: pick Grok 4.6 (Medium) when you need intelligence above 6.3, and Celeris-1 when 6.3 is enough.
| Metric | Celeris-1 | Grok 4.6 (Medium) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.3 | 42.8 | +579.4% Grok 4.6 (Medium) is 6.8× more intelligent |
| Total AA cost (lower is better) | $59.99 | $1,557.04 | +2495.5% Grok 4.6 (Medium) is 26× more expensive |
| End-to-end time (lower is better) | 0.87s | 31.56s | +3527.6% Grok 4.6 (Medium) is 3527.6% slower |
| Price per 1M tokens (in / out) | $0.20 / $0.70 | $2.00 / $6.00 | |
| Input modalities | Text, Image | Text, Image |
Grok 4.6 (Medium) vs Celeris-1: 579.4% more intelligence, 2495.5% more cost to run the AA benchmark, and 3527.6% 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.
- Grok 4.6 (Medium) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Celeris-1Grok 4.6 (Medium)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/grok-4-6-medium · Markdown: /api/v1/compare/celeris-1/grok-4-6-medium?format=md · llms.txt · agent skill