GPT-6 Luna Max vs Mistral Large 4 Preview compared

GPT-6 Luna Max leads the intelligence index 27.9 to 25.3. GPT-6 Luna Max costs 81% less on blended price. Compare price, speed, latency and a clear verdict.

Metric	GPT-6 Luna (Max)	Mistral Large 4 Preview
Intelligence Index	27.9	25.3
Input price (per 1M tokens)	$0.10	$0.70
Output price (per 1M tokens)	$0.50	$2.10
Output speed (tokens/s)	121	130
Time to first token	2.0 min	1.9s
Release date	2026-09-22	2026-10-06

Metric

GPT-6 Luna (Max)

Mistral Large 4 Preview

Intelligence Index

27.9

25.3

Input price (per 1M tokens)

$0.10

$0.70

Output price (per 1M tokens)

$0.50

$2.10

Output speed (tokens/s)

121

130

Time to first token

2.0 min

1.9s

Release date

2026-09-22

2026-10-06

If you only looked at the intelligence index, GPT-6 Luna (Max) and Mistral Large 4 Preview would be hard to tell apart. Mistral Large 4 Preview starts answering far sooner, with a time to first token of 1.9 seconds compared with 2.0 minutes for GPT-6 Luna Max. All numbers are the catalogue's recorded values; nobody ran either model by hand for this page.

Speed and latency

Once a response is under way, GPT-6 Luna Max produces roughly 121 tokens per second against 130 tokens per second for Mistral Large 4 Preview. Throughput is close to level. Before any text appears, GPT-6 Luna Max takes 2.0 minutes and Mistral Large 4 Preview 1.9 seconds. In an interactive app, Mistral Large 4 Preview will feel noticeably more responsive. Waits that long are felt on every chat-style request, though they matter less for batch jobs.

Put together, a 2,000-token answer would take about 2.3 minutes from GPT-6 Luna Max and 17 seconds from Mistral Large 4 Preview, counting the first-token wait.

Which is newer

Mistral Large 4 Preview arrived on October 6, 2026, 14 days after GPT-6 Luna Max (September 22, 2026). They are effectively contemporaries.

Token pricing and a sample bill

Per million tokens, GPT-6 Luna Max charges $0.10 for input and $0.50 for output, while Mistral Large 4 Preview charges $0.70 and $2.10. That makes GPT-6 Luna Max's output 76% cheaper.

A reference job of 1 million input tokens and 200,000 output tokens costs $0.20 with GPT-6 Luna Max and $1.12 with Mistral Large 4 Preview, so GPT-6 Luna Max saves $0.92. For classifying 100,000 short messages at 150 input tokens and 5 output tokens each, GPT-6 Luna Max would come in 85% lower: $1.75 for GPT-6 Luna Max against $11.55 for Mistral Large 4 Preview.

Benchmark scores

On the intelligence index, GPT-6 Luna Max scores 27.9 against 25.3 for Mistral Large 4 Preview. It is a small margin for an index that averages many evaluations.

Across the 109 active models with an intelligence score in the catalogue, GPT-6 Luna Max ranks 62nd and Mistral Large 4 Preview ranks 67th.

The catalogue does not yet split either model's score into coding and math indexes.

Value for money

Per point of intelligence index, GPT-6 Luna Max costs $0.0072 of blended price per million tokens and Mistral Large 4 Preview $0.042. GPT-6 Luna Max scores higher and costs less per point, so on price per point there is nothing to trade off.

Common questions about GPT-6 Luna Max and Mistral Large 4 Preview

Is GPT-6 Luna Max better than Mistral Large 4 Preview?

Not across the board: GPT-6 Luna Max scores higher on the intelligence index, 27.9 to 25.3; GPT-6 Luna Max is 81% cheaper on blended price; and Mistral Large 4 Preview reaches its first token sooner.

Which is cheaper, GPT-6 Luna Max or Mistral Large 4 Preview?

GPT-6 Luna Max is cheaper on a blended basis. GPT-6 Luna Max lists $0.10 per million input tokens and $0.50 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 $0.20 against $1.12.

Are GPT-6 Luna Max and Mistral Large 4 Preview from the same company?

GPT-6 Luna Max is made by OpenAI and Mistral Large 4 Preview by Mistral. GPT-6 Luna Max was released on September 22, 2026 and Mistral Large 4 Preview on October 6, 2026.

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, GPT-6 Luna Max or Mistral Large 4 Preview?

Their output speeds are close: 121 tokens per second for GPT-6 Luna Max and 130 tokens per second for Mistral Large 4 Preview. Mistral Large 4 Preview reaches its first token sooner (1.9 seconds against 2.0 minutes).

Final whistle

In one line: GPT-6 Luna Max is the stronger all-round pick on this data, while Mistral Large 4 Preview makes sense in narrower cases. Pick Mistral Large 4 Preview if users are waiting on the first word. Pick GPT-6 Luna Max if cost matters ($0.50 against $2.10 per million output tokens) and you need the higher overall score (27.9 against 25.3).

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 GPT-6 Luna (Max) and Mistral Large 4 Preview pages. The AI Benchmark methodology explains how that data is collected and shown.