GLM-5.3 Max vs Mistral Large 4 High compared

GLM-5.3 Max leads the intelligence index 31.7 to 26.1. Price per token, response speed and when to pick each.

Metric	GLM-5.3 (Max)	Mistral Large 4 (High)
Intelligence Index	31.7	26.1
Input price (per 1M tokens)	$1.40	$0.70
Output price (per 1M tokens)	$4.40	$2.10
Output speed (tokens/s)	74	139
Time to first token	1.7s	1.7s
Release date	2026-08-18	2026-10-29

Metric

GLM-5.3 (Max)

Mistral Large 4 (High)

Intelligence Index

31.7

26.1

Input price (per 1M tokens)

$1.40

$0.70

Output price (per 1M tokens)

$4.40

$2.10

Output speed (tokens/s)

139

Time to first token

1.7s

Release date

2026-08-18

2026-10-29

Here is how GLM-5.3 (Max), built by Z AI, lines up against Mistral Large 4 (High) from Mistral. The biggest gap is output speed, where Mistral Large 4 High records 139 tokens per second and GLM-5.3 Max 74 tokens per second. The figures come from tracked catalogue data, not from our own testing, so treat them as a starting point for a trial on your tasks.

Mistral Large 4 High is the faster writer

Measured output speed is 74 tokens per second for GLM-5.3 Max and 139 tokens per second for Mistral Large 4 High. Mistral Large 4 High is ahead by 89% on throughput. Time to first token is 1.7 seconds for GLM-5.3 Max and 1.7 seconds for Mistral Large 4 High.

Put together, an 800-token answer would take about 13 seconds from GLM-5.3 Max and 7.5 seconds from Mistral Large 4 High, counting the first-token wait. Counting that wait, Mistral Large 4 High only pulls ahead on outputs beyond about 50 tokens.

Release timing

Mistral Large 4 High arrived on October 29, 2026, about 2 months after GLM-5.3 Max (August 18, 2026).

Token pricing and a sample bill

The list prices are $1.40 in and $4.40 out for GLM-5.3 Max, and $0.70 in and $2.10 out for Mistral Large 4 High, per million tokens. That makes Mistral Large 4 High's output 52% cheaper.

A reference job of 1 million input tokens and 200,000 output tokens costs $2.28 with GLM-5.3 Max and $1.12 with Mistral Large 4 High, so Mistral Large 4 High saves $1.16. A bigger example, extracting fields from 20,000 pages of 1,500 tokens into 150-token records, costs $55.20 on GLM-5.3 Max and $27.30 on Mistral Large 4 High: a gap of $27.90. On a 3:1 blend of input to output tokens, that works out to $2.15 versus $1.05 per million.

Overall capability: 5.6 points apart

The catalogue puts GLM-5.3 Max at 31.7 and Mistral Large 4 High at 26.1 on its intelligence index. That is a clear margin for an index that averages many evaluations.

Among 109 active scored models, GLM-5.3 Max sits 47th and Mistral Large 4 High 65th.

Specialist coding and math indexes are missing for both, so treat the overall score as the only capability signal here.

Cost per point of intelligence

Per point of intelligence index, GLM-5.3 Max costs $0.068 of blended price per million tokens and Mistral Large 4 High $0.040. Mistral Large 4 High delivers each index point for 41% less; whether GLM-5.3 Max's extra 5.6 points are worth the premium depends on how often your tasks need them.

Common questions about GLM-5.3 Max and Mistral Large 4 High

Is GLM-5.3 Max better than Mistral Large 4 High?

Neither wins everywhere: GLM-5.3 Max scores higher on the intelligence index, 31.7 to 26.1; Mistral Large 4 High is 51% cheaper on blended price; and Mistral Large 4 High streams output 1.9 times as fast.

Are GLM-5.3 Max and Mistral Large 4 High from the same company?

GLM-5.3 Max is made by Z AI and Mistral Large 4 High by Mistral. GLM-5.3 Max was released on August 18, 2026 and Mistral Large 4 High on October 29, 2026.

Where do these numbers come from?

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.

How much do GLM-5.3 Max and Mistral Large 4 High cost?

Mistral Large 4 High is cheaper on a blended basis. GLM-5.3 Max lists $1.40 per million input tokens and $4.40 per million output tokens; Mistral Large 4 High lists $0.70 and $2.10. For 1 million input and 200,000 output tokens that is $2.28 against $1.12.

When were GLM-5.3 Max and Mistral Large 4 High released?

Mistral Large 4 High is newer. It was released on October 29, 2026, about 2 months after GLM-5.3 Max (August 18, 2026).

Final whistle

This one is genuinely split between GLM-5.3 Max and Mistral Large 4 High, and the right answer depends on which trade-off you can live with. Pick GLM-5.3 Max if you need the higher overall score (31.7 against 26.1). Pick Mistral Large 4 High if cost matters ($2.10 against $4.40 per million output tokens) and your outputs often run past about 50 tokens.

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 GLM-5.3 (Max) and Mistral Large 4 (High) pages. The AI Benchmark methodology explains how that data is collected and shown.