Grok 4.20 0309 v2 (Non-reasoning) vs Grok 4.3 (High)

Grok 4.20 0309 v2 (Non-reasoning) vs Grok 4.3 (High). A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

SpaceXAIGrok 4.20 0309 v2 (Non-reasoning)Not ranked · benchmark data missing
Intelligence
14.20
Total cost
-
SpaceXAIGrok 4.3 (High)Off the frontier
Intelligence
24.90
Total cost
$363
Verdict

Comparison incomplete

A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

MetricGrok 4.20 0309 v2 (Non-reasoning)Grok 4.3 (High)Difference
Intelligence (higher is better)14.224.9+75.4% Grok 4.3 (High) is 75.4% more intelligent
Total AA cost (lower is better)Not reported$363.24— not comparable
End-to-end time (lower is better)5.15s28.87s+460.6% Grok 4.3 (High) is 460.6% slower
Price per 1M tokens (in / out)$1.25 / $2.50$1.25 / $2.50
Input modalitiesText, ImageText, Image
Open this matchup in the interactive pickerGrok 4.20 0309 v2 (Non-reasoning): what beats itGrok 4.3 (High): what beats it
Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/grok-4-20-non-reasoning/grok-4-3 · Markdown: /api/v1/compare/grok-4-20-non-reasoning/grok-4-3?format=md · llms.txt · agent skill