MiMo-V2.6-Pro vs Mistral Large 4 Preview: which is faster?

MiMo-V2.6-Pro leads the intelligence index 29.9 to 25.3. MiMo-V2.6-Pro costs 48% less on blended price. Benchmarks, sample bills, speed and a verdict.

Metric	MiMo-V2.6-Pro	Mistral Large 4 Preview
Intelligence Index	29.9	25.3
Input price (per 1M tokens)	$0.435	$0.70
Output price (per 1M tokens)	$0.87	$2.10
Output speed (tokens/s)	41	130
Time to first token	3.0s	1.9s
Release date	2026-09-21	2026-10-06

Metric

MiMo-V2.6-Pro

Mistral Large 4 Preview

Intelligence Index

29.9

25.3

Input price (per 1M tokens)

$0.435

$0.70

Output price (per 1M tokens)

$0.87

$2.10

Output speed (tokens/s)

130

Time to first token

3.0s

1.9s

Release date

2026-09-21

2026-10-06

Choosing between MiMo-V2.6-Pro and Mistral Large 4 Preview also means choosing between Xiaomi and Mistral. This page is written automatically from catalogue numbers only: benchmark scores, list prices and measured speed. Throughput is the standout difference: 130 tokens per second for Mistral Large 4 Preview against 41 tokens per second for MiMo-V2.6-Pro.

How fast they respond

MiMo-V2.6-Pro generates about 41 tokens per second and Mistral Large 4 Preview about 130 tokens per second. Mistral Large 4 Preview is ahead by 216% on throughput. Before any text appears, MiMo-V2.6-Pro takes 3.0 seconds and Mistral Large 4 Preview 1.9 seconds. Mistral Large 4 Preview gets to its first token 1.6 times as fast.

Add the two numbers up for an 800-token reply and Mistral Large 4 Preview finishes first: 23 seconds for MiMo-V2.6-Pro, 8.1 seconds for Mistral Large 4 Preview.

Price per token

The list prices are $0.435 in and $0.87 out for MiMo-V2.6-Pro, and $0.70 in and $2.10 out for Mistral Large 4 Preview, per million tokens. Mistral Large 4 Preview costs 2.4 times as much per output token.

For a sample workload of 1 million input tokens and 200,000 output tokens, MiMo-V2.6-Pro would cost $0.61 and Mistral Large 4 Preview $1.12, a difference of $0.51. For writing 2,000 drafts of 2,000 output tokens from 300-token prompts, MiMo-V2.6-Pro would come in 58% lower: $3.74 for MiMo-V2.6-Pro against $8.82 for Mistral Large 4 Preview. On a 3:1 blend of input to output tokens, that works out to $0.544 versus $1.05 per million.

Which is newer

The release dates are September 21, 2026 for MiMo-V2.6-Pro and October 6, 2026 for Mistral Large 4 Preview, 15 days apart. They are effectively contemporaries.

How the intelligence index compares

MiMo-V2.6-Pro records 29.9 on the intelligence index and Mistral Large 4 Preview records 25.3. That is a clear margin for an index that averages many evaluations.

Among 109 active scored models, MiMo-V2.6-Pro sits 55th and Mistral Large 4 Preview 67th.

For coding or maths work specifically, the catalogue has no dedicated index on either side yet.

Value for money

A blunt value measure, blended price over intelligence score, puts MiMo-V2.6-Pro at $0.018 and Mistral Large 4 Preview at $0.042 per point. With the higher score and the lower cost per point, MiMo-V2.6-Pro is the better value per point on these numbers.

Quick answers

Is Mistral Large 4 Preview better than MiMo-V2.6-Pro?

It depends on what you need: MiMo-V2.6-Pro scores higher on the intelligence index, 29.9 to 25.3; MiMo-V2.6-Pro is 48% cheaper on blended price; and Mistral Large 4 Preview streams output 3.2 times as fast.

Are MiMo-V2.6-Pro and Mistral Large 4 Preview from the same company?

MiMo-V2.6-Pro is made by Xiaomi and Mistral Large 4 Preview by Mistral. MiMo-V2.6-Pro was released on September 21, 2026 and Mistral Large 4 Preview on October 6, 2026.

Which is cheaper, MiMo-V2.6-Pro or Mistral Large 4 Preview?

MiMo-V2.6-Pro is cheaper on a blended basis. MiMo-V2.6-Pro lists $0.435 per million input tokens and $0.87 per million output tokens; Mistral Large 4 Preview lists $0.70 and $2.10. For 1 million input and 200,000 output tokens that is $0.61 against $1.12.

Was this comparison tested by hand?

The figures are the recorded benchmark, price and speed data in Franklin AI's model catalogue. This page is written from that data automatically; neither model was tested by hand for it.

Which model has lower latency?

Mistral Large 4 Preview generates output faster, at 130 tokens per second against 41 tokens per second. Mistral Large 4 Preview reaches its first token sooner (1.9 seconds against 3.0 seconds).

Final whistle

Bottom line: MiMo-V2.6-Pro is the stronger all-round pick on this data, while Mistral Large 4 Preview makes sense in narrower cases. Pick MiMo-V2.6-Pro if you need the higher overall score (29.9 against 25.3) and cost matters ($0.87 against $2.10 per million output tokens). Pick Mistral Large 4 Preview if long outputs need to finish quickly and users are waiting on the first word.

Where the numbers come from

The scores, speed and prices in this comparison come from independent third-party model evaluations that Franklin AI syncs each day, and the article was written from a snapshot of them. For the latest results, open the MiMo-V2.6-Pro and Mistral Large 4 Preview pages. The AI Benchmark methodology explains how that data is collected and shown.