Head-to-head AI model comparison graphic: Mistral Large 4 (Mistral) vs Mistral Large 4 Preview (Mistral). Intelligence index 26.1 vs 25.3; output speed 139 vs 130 tokens per second; time to first token 1.7s vs 1.9s; output price $2.10 vs $2.10 per million tokens; input price $0.70 vs $0.70 per million tokens. franklineh.com
Mistral Large 4 vs Mistral Large 4 Preview: head-to-head AI benchmark comparison. Mistral Large 4 leads on intelligence index, output speed and time to first token; level on output price and input price.
Head to headBy Franklin AIUpdated

Mistral Large 4 High vs Mistral Large 4 Preview compared

Mistral Large 4 High leads the intelligence index 26.1 to 25.3. Compare price, speed, latency and a clear verdict.

Pick it for Mistral Large 4 · High

  • Only if a test on your own tasks shows an advantage this data does not capture; on the recorded numbers Mistral Large 4 Preview is ahead or level everywhere.

Pick it for Mistral Large 4 Preview

  • Only if a test on your own tasks shows an advantage this data does not capture; on the recorded numbers Mistral Large 4 High is ahead or level everywhere.

By the numbers

MetricMistral Large 4 (High)Mistral Large 4 Preview
Intelligence Index26.125.3
Input price (per 1M tokens)$0.70$0.70
Output price (per 1M tokens)$2.10$2.10
Output speed (tokens/s)139130
Time to first token1.7s1.9s
Release date2026-10-292026-10-06

Mistral Large 4 (High) and Mistral Large 4 Preview both come from Mistral, so this is a choice inside one lineup rather than between vendors. The biggest separation is in overall capability: 26.1 for Mistral Large 4 High against 25.3 for Mistral Large 4 Preview. No hands-on testing went into this write-up; it summarises the recorded benchmark, price and speed data for both models.

Mistral Large 4 High leads on the intelligence index

Mistral Large 4 High records 26.1 on the intelligence index and Mistral Large 4 Preview records 25.3. A gap that small is inside the range where one aggregate cannot name a winner.

Across the 109 active models with an intelligence score in the catalogue, Mistral Large 4 High ranks 65th and Mistral Large 4 Preview ranks 67th.

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

Generation gap

The release dates are October 6, 2026 for Mistral Large 4 Preview and October 29, 2026 for Mistral Large 4 High, 23 days apart. They are effectively contemporaries.

Pricing: no difference

Per million tokens, Mistral Large 4 High charges $0.70 for input and $2.10 for output, while Mistral Large 4 Preview charges $0.70 and $2.10. The rates are identical, so price will not separate them.

Cost per point of intelligence

Per point of intelligence index, Mistral Large 4 High costs $0.040 of blended price per million tokens and Mistral Large 4 Preview $0.042. On that measure they are priced in proportion to their scores.

Speed and latency

Mistral Large 4 High generates about 139 tokens per second and Mistral Large 4 Preview about 130 tokens per second. There is little to choose between them on raw output speed. Before any text appears, Mistral Large 4 High takes 1.7 seconds and Mistral Large 4 Preview 1.9 seconds.

Add the two numbers up for a 400-token reply and Mistral Large 4 High finishes first: 4.6 seconds for Mistral Large 4 High, 5.0 seconds for Mistral Large 4 Preview.

FAQ

Is Mistral Large 4 High better than Mistral Large 4 Preview?

Mistral Large 4 High leads on every measure the catalogue separates: Mistral Large 4 High scores higher on the intelligence index, 26.1 to 25.3; and their blended prices are about the same.

Which is newer, Mistral Large 4 High or Mistral Large 4 Preview?

Mistral Large 4 High is newer. It was released on October 29, 2026, 23 days after Mistral Large 4 Preview (October 6, 2026).

How much do Mistral Large 4 High and Mistral Large 4 Preview cost?

They cost about the same. Mistral Large 4 High lists $0.70 in and $2.10 out per million tokens, and Mistral Large 4 Preview lists $0.70 and $2.10.

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 is faster, Mistral Large 4 High or Mistral Large 4 Preview?

Their output speeds are close: 139 tokens per second for Mistral Large 4 High and 130 tokens per second for Mistral Large 4 Preview. Time to first token is similar: 1.7 seconds and 1.9 seconds.

Final whistle

The verdict: the recorded data does not separate Mistral Large 4 High and Mistral Large 4 Preview on capability, price or speed, so decide on a short trial with your own prompts.

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 Mistral Large 4 (High) and Mistral Large 4 Preview pages. The AI Benchmark methodology explains how that data is collected and shown.

Comments (0)

No comments yet

Be the first to share your thoughts!