AI Benchmark Model

Grok 4.6 (xhigh)

Benchmark scores, pricing, speed, and model comparisons for Grok 4.6 (xhigh).

Key scores

Intelligence60.0Index score
Coding75.9Index score
Speed66.2Tokens/sec
Blended Cost$3.00Per 1M tokens

Grok 4.6 (xhigh), developed by SpaceXAI and released on August 12, 2026, is an artificial intelligence model evaluated across several standardized performance metrics. The model holds an intelligence index of 60 and a coding index of 75.9, while its math index remains unknown. Benchmark results for the model include a GPQA score of 0.935, an HLE score of 0.441, a SciCode score of 0.516, and an LCR score of 0.756666666666667. In terms of operational performance, the model achieves an output speed of 66.199 tokens per second with a time to first token of 42.934 seconds. Pricing for Grok 4.6 (xhigh) is set at $2.00 per million input tokens and $6.00 per million output tokens, resulting in a blended rate of $3.00 per million tokens.

Benchmark results

4 tracked benchmark rows for Grok 4.6 (xhigh).

GPQA Reasoning
93.5%
LCR Other
75.7%
SciCode Other
51.6%
HLE Other
44.1%

Comments (0)

No comments yet

Be the first to share your thoughts!