Grok 4.20 Benchmark Details

Grok 4.20 currently shows benchmark results led by Context Arena (81 / 126, score 54), ARC-AGI-3 (9 / 9, score 0). This page also tracks comparisons against 1 predecessor or same-series models.

Benchmark Results

Grok 4.20

Benchmark Results

Text Embedding

2 evaluations

Benchmark / mode

Score

Rank/total

Context Arena

Standard Mode

20.32

123 / 126

Context Arena

Thinking Mode

81 / 126

General Knowledge

1 evaluations

Benchmark / mode

Score

Rank/total

ARC-AGI-3

Thinking Mode

9 / 9

Compare with other models

Version History

How each version of the Grok 4.20 series stacks up on benchmark tests

Grok 4.20Grok 4.1

No benchmark data matches the selected filters.

Standard API Pricing Across the Grok 4.20 Series

Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.

Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens

When a context threshold exists, the charted base price only applies within these limits:

Grok 4.20: Base price applies to <= 200000

Model	Supplier	Standard input	Standard output	Base price applies to
Grok 4.20	xAI	$1.25 / 1M tokens	$2.5 / 1M tokens	<= 200000