GPT-6 Luna (Non-reasoning) vs Grok 4.3 (High)
Which is better for the money: GPT-6 Luna (Non-reasoning) by OpenAI or Grok 4.3 (High) by SpaceXAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Trade-off
Verdict
Depends on your budget
Grok 4.3 (High) scores 6.4 points higher (24.9 vs 18.5) but costs 19× as much to run the benchmark ($363 vs $19.2; mid-range vs budget cost classes). They are not alternatives at one budget: pick Grok 4.3 (High) when you need intelligence above 18.5, and GPT-6 Luna (Non-reasoning) when 18.5 is enough.
| Metric | GPT-6 Luna (Non-reasoning) | Grok 4.3 (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 18.5 | 24.9 | +34.6% Grok 4.3 (High) is 34.6% more intelligent |
| Total AA cost (lower is better) | $19.16 | $363.24 | +1795.8% Grok 4.3 (High) is 19× more expensive |
| End-to-end time (lower is better) | 5.09s | 30.35s | +496.3% Grok 4.3 (High) is 496.3% slower |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $1.25 / $2.50 | |
| Input modalities | Text, Image | Text, Image |
Grok 4.3 (High) vs GPT-6 Luna (Non-reasoning): 34.6% more intelligence, 1795.8% more cost to run the AA benchmark, and 496.3% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6 Luna (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- Grok 4.3 (High) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
GPT-6 Luna (Non-reasoning)Grok 4.3 (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/gpt-6-luna-non-reasoning/grok-4-3 · Markdown: /api/v1/compare/gpt-6-luna-non-reasoning/grok-4-3?format=md · llms.txt · agent skill