Grok 4.6 Xhigh vs MiMo-V2.6-Pro: cost and benchmark comparison

On the headline score, SpaceXAI's Grok 4.6 (Xhigh) and Xiaomi's MiMo-V2.6-Pro are almost level. This page is written automatically from catalogue numbers only: benchmark scores, list prices and measured speed. The sharpest difference is price: MiMo-V2.6-Pro costs $0.87 per million output tokens, against $6.00 for Grok 4.6 Xhigh.

Cost: MiMo-V2.6-Pro is cheaper

Grok 4.6 Xhigh lists $2.00 per million input tokens and $6.00 per million output tokens; MiMo-V2.6-Pro lists $0.435 and $0.87. That makes MiMo-V2.6-Pro's output 86% cheaper.

For a sample workload of 1 million input tokens and 200,000 output tokens, Grok 4.6 Xhigh would cost $3.20 and MiMo-V2.6-Pro $0.61, a difference of $2.59. For classifying 100,000 short messages at 150 input tokens and 5 output tokens each, MiMo-V2.6-Pro would come in 79% lower: $33.00 for Grok 4.6 Xhigh against $6.96 for MiMo-V2.6-Pro. On a 3:1 blend of input to output tokens, that works out to $3.00 versus $0.544 per million.

Generation gap

MiMo-V2.6-Pro arrived on September 21, 2026, 40 days after Grok 4.6 Xhigh (August 12, 2026). That is close enough to count them as the same generation.

Waiting time

Measured output speed is 62 tokens per second for Grok 4.6 Xhigh and 41 tokens per second for MiMo-V2.6-Pro. Grok 4.6 Xhigh is ahead by 50% on throughput. The wait for the first token averages 47 seconds on Grok 4.6 Xhigh against 3.0 seconds on MiMo-V2.6-Pro. So the two pull in opposite directions, with MiMo-V2.6-Pro quicker off the mark and Grok 4.6 Xhigh quicker once it gets going; the crossover is around 5,400 tokens. Waits that long are felt on every chat-style request, though they matter less for batch jobs.

For a 1,500-token response, first token plus generation comes to roughly 71 seconds on Grok 4.6 Xhigh and 40 seconds on MiMo-V2.6-Pro.

How the intelligence index compares

The catalogue puts Grok 4.6 Xhigh at 31.0 and MiMo-V2.6-Pro at 29.9 on its intelligence index. That is a modest edge: real, but small enough that the right set of tasks could reverse it. In relative terms, Grok 4.6 Xhigh scores 4% higher.

Across the 109 active models with an intelligence score in the catalogue, Grok 4.6 Xhigh ranks 49th and MiMo-V2.6-Pro ranks 55th.

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

Value for money

Per point of intelligence index, Grok 4.6 Xhigh costs $0.097 of blended price per million tokens and MiMo-V2.6-Pro $0.018. Grok 4.6 Xhigh costs 5.3 times as much per point, which is the price of its lead.