Grok 4.6 Xhigh vs Mistral Large 4 High: which responds faster?

Here is how Grok 4.6 (Xhigh), built by SpaceXAI, lines up against Mistral Large 4 (High) from Mistral. The widest gap is the wait for the first token: 1.7 seconds for Mistral Large 4 High against 47 seconds for Grok 4.6 Xhigh. This page is written automatically from catalogue numbers only: benchmark scores, list prices and measured speed.

Throughput and time to first token

Once a response is under way, Grok 4.6 Xhigh produces roughly 62 tokens per second against 139 tokens per second for Mistral Large 4 High. On long outputs, that is a real advantage for Mistral Large 4 High. Before any text appears, Grok 4.6 Xhigh takes 47 seconds and Mistral Large 4 High 1.7 seconds. Grok 4.6 Xhigh waits 27 times as long before its first token. A first-token wait of that length suits background work better than live conversation.

Put together, a 2,000-token answer would take about 79 seconds from Grok 4.6 Xhigh and 16 seconds from Mistral Large 4 High, counting the first-token wait.

Overall capability: 4.9 points apart

Grok 4.6 Xhigh comes out ahead on the intelligence index, 31.0 to 26.1. A lead of this size is hard to dismiss as noise. In relative terms, Grok 4.6 Xhigh scores 19% higher.

Across the 109 active models with an intelligence score in the catalogue, Grok 4.6 Xhigh ranks 49th and Mistral Large 4 High ranks 65th.

There are no coding or math index scores for either model in the catalogue, which keeps this comparison at the aggregate level.

Price per token

The list prices are $2.00 in and $6.00 out for Grok 4.6 Xhigh, and $0.70 in and $2.10 out for Mistral Large 4 High, per million tokens. Grok 4.6 Xhigh costs 2.9 times as much per output token.

Take 1 million input tokens and 200,000 output tokens: that comes to $3.20 on Grok 4.6 Xhigh and $1.12 on Mistral Large 4 High. For an agent that reads 50 million tokens and writes 5 million in a month, Mistral Large 4 High would come in 65% lower: $130 for Grok 4.6 Xhigh against $45.50 for Mistral Large 4 High. Blended at three input tokens per output token, the effective rates are $3.00 for Grok 4.6 Xhigh and $1.05 for Mistral Large 4 High.

Cost per point of intelligence

Per point of intelligence index, Grok 4.6 Xhigh costs $0.097 of blended price per million tokens and Mistral Large 4 High $0.040. Mistral Large 4 High delivers each index point for 58% less; whether Grok 4.6 Xhigh's extra 4.9 points are worth the premium depends on how often your tasks need them.

When they came out

The release dates are August 12, 2026 for Grok 4.6 Xhigh and October 29, 2026 for Mistral Large 4 High, about 3 months apart.