Grok 4.6 (Xhigh) vs Grok 4.7 (High)
Which is better for the money: Grok 4.6 (Xhigh) by SpaceXAI or Grok 4.7 (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 4.7 (High) scores 2.1 points higher (46.3 vs 44.2) but costs 1.7× as much to run the benchmark ($3881 vs $2242; both flagship class). Pick Grok 4.7 (High) when the extra intelligence is worth the premium, otherwise Grok 4.6 (Xhigh).
| Metric | Grok 4.6 (Xhigh) | Grok 4.7 (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 44.2 | 46.3 | +4.8% Grok 4.7 (High) is 4.8% more intelligent |
| Total AA cost (lower is better) | $2,241.91 | $3,880.88 | +73.1% Grok 4.7 (High) is 73.1% more expensive |
| End-to-end time (lower is better) | 37.86s | 31.16s | −17.7% Grok 4.7 (High) is 17.7% faster |
| Price per 1M tokens (in / out) | $2.00 / $6.00 | $2.00 / $6.00 | |
| Input modalities | Text, Image | Text, Image |
Grok 4.7 (High) vs Grok 4.6 (Xhigh): 4.8% more intelligence, 73.1% more cost to run the AA benchmark, and 17.7% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Grok 4.6 (Xhigh) is off the frontier: at the same or lower cost, Claude Opus 5.5 (High, Default Fallback) scores 53.60 for $2172.
- Grok 4.7 (High) is off the frontier: at the same or lower cost, Kimi K3.1 Pro scores 55.10 for $3117.
Grok 4.6 (Xhigh)Grok 4.7 (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/grok-4-6-xhigh/grok-4-7-high · Markdown: /api/v1/compare/grok-4-6-xhigh/grok-4-7-high?format=md · llms.txt · agent skill