The AI arena is free today

Open Superagent

Mistral Large 4 vs Mistral Large 3 (675B Instruct 2512)

Mistral Large 4 leads the LLM Stats Score 46.2 to 9.0. Mistral Large 3 (675B Instruct 2512) is 1.4x cheaper per token.

Mistral AI · Mistral AI · Updated for 2026

Which is better?

Mistral Large 4 leads the overall LLM Stats Score 46.2 to 9.0, ranking #34 overall.

On price, Mistral Large 3 (675B Instruct 2512) is roughly 1.4x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Mistral Large 4 also accepts a larger context window (1,000,000 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Mistral Large 4

  • overall performance matters — it scores 46.2 and ranks #34 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you process long inputs — it offers a 1,000,000 token context window
  • you want the most recent training data — it shipped Oct 2026

Choose Mistral Large 3 (675B Instruct 2512)

  • cost matters — it's about 1.4x cheaper per token
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Mistral Large 4
Mistral AI
Mistral Large 3 (675B Instruct 2512)
Mistral AI
Core performance indexes
LLM Stats Score
46.2
#34
9.0
#286
Reasoning
44.4
#38
9.2
#280
Coding
35.4
#27
1.4
#245
Cost, coverage & limits
Benchmark wins
—
—
Input price
$0.68 / M
$0.50 / M
Output price
$2.09 / M
$1.50 / M
Context window
1,000,000
262,100

Individual benchmarks

18 reported for Mistral Large 4 · 5 for Mistral Large 3 (675B Instruct 2512)

No common benchmarks found

Mistral Large 4 and Mistral Large 3 (675B Instruct 2512)don't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Mistral Large 3 (675B Instruct 2512) costs less

For input processing, Mistral Large 4 ($0.68/1M tokens) is 1.4x more expensive than Mistral Large 3 (675B Instruct 2512) ($0.50/1M tokens).

For output processing, Mistral Large 4 ($2.09/1M tokens) is 1.4x more expensive than Mistral Large 3 (675B Instruct 2512) ($1.50/1M tokens).

In conclusion, Mistral Large 4 is more expensive than Mistral Large 3 (675B Instruct 2512).*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Thu Oct 15 2026 • llm-stats.com
Mistral AI
Mistral Large 4
Input tokens$0.68
Output tokens$2.09
Best providerMistral
Mistral AI
Mistral Large 3 (675B Instruct 2512)
Input tokens$0.50
Output tokens$1.50
Best providerMistral
Notice missing or incorrect data?

Model Size

Parameter count comparison

375.0B diff

Mistral Large 4 has 375.0B more parameters than Mistral Large 3 (675B Instruct 2512), making it 55.6% larger.

Mistral AI
Mistral Large 4
1.1Tparameters
Mistral AI
Mistral Large 3 (675B Instruct 2512)
675.0Bparameters
1050.0B
Mistral Large 4
675.0B
Mistral Large 3 (675B Instruct 2512)

Context Window

Maximum input and output token capacity

Mistral Large 4 accepts 1,000,000 input tokens compared to Mistral Large 3 (675B Instruct 2512)'s 262,100 tokens. Only Mistral Large 3 (675B Instruct 2512) specifies output context (262,100 tokens).

Mistral AI
Mistral Large 4
Input1,000,000 tokens
Output- tokens
Mistral AI
Mistral Large 3 (675B Instruct 2512)
Input262,100 tokens
Output262,100 tokens
Thu Oct 15 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Mistral Large 4 and Mistral Large 3 (675B Instruct 2512) support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Mistral Large 4

Text
Images
Audio
Video

Mistral Large 3 (675B Instruct 2512)

Text
Images
Audio
Video

License

Usage and distribution terms

Mistral Large 4 is licensed under a proprietary license, while Mistral Large 3 (675B Instruct 2512) uses Apache 2.0.

License differences may affect how you can use these models in commercial or open-source projects.

Mistral Large 4

Proprietary

Closed source

Mistral Large 3 (675B Instruct 2512)

Apache 2.0

Open weights

Release Timeline

When each model was launched

Mistral Large 4 was released on 2026-10-06, while Mistral Large 3 (675B Instruct 2512) was released on 2025-12-04.

Mistral Large 4 is 10 months newer than Mistral Large 3 (675B Instruct 2512).

Mistral Large 4

Oct 6, 2026

1 weeks ago

10mo newer
Mistral Large 3 (675B Instruct 2512)

Dec 4, 2025

10 months ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

Mistral Large 4 is available from Mistral AI. Mistral Large 3 (675B Instruct 2512) is available from Mistral AI.

Mistral Large 4

mistral logo
Mistral
Input Price:Input: $0.68/1MOutput Price:Output: $2.09/1M

Mistral Large 3 (675B Instruct 2512)

mistral logo
Mistral
Input Price:Input: $0.50/1MOutput Price:Output: $1.50/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Mistral Large 4 and Mistral Large 3 (675B Instruct 2512) side-by-side, then vote on the output you prefer.

Mistral Large 4
✓ Preferred
Mistral Large 3 (675B Instruct 2512)
Open in Playground

FAQ

Common questions about Mistral Large 4 vs Mistral Large 3 (675B Instruct 2512).

Which is better, Mistral Large 4 or Mistral Large 3 (675B Instruct 2512)?

Mistral Large 4 leads the LLM Stats Score 46.2 to 9.0. Mistral Large 4 is made by Mistral AI and Mistral Large 3 (675B Instruct 2512) is made by Mistral AI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Mistral Large 4 compare to Mistral Large 3 (675B Instruct 2512) in benchmarks?

Mistral Large 4 scores B3 AI Security Benchmark: 93.3%, CyBench: 93.0%, SciCode: 91.8%, KORABench: 84.5%, CyberGym: 82.0%. Mistral Large 3 (675B Instruct 2512) scores MMMLU: 85.5%, AMC_2022_23: 52.0%, GPQA: 43.9%, LiveCodeBench: 34.4%, SimpleQA: 23.8%.

Is Mistral Large 4 cheaper than Mistral Large 3 (675B Instruct 2512)?

Mistral Large 3 (675B Instruct 2512) is 1.4x cheaper for input tokens. Mistral Large 4 costs $0.68/M input and $2.09/M output via mistral. Mistral Large 3 (675B Instruct 2512) costs $0.50/M input and $1.50/M output via mistral.

What are the context window sizes for Mistral Large 4 and Mistral Large 3 (675B Instruct 2512)?

Mistral Large 4 supports 1.0M tokens and Mistral Large 3 (675B Instruct 2512) supports 262K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Mistral Large 4 and Mistral Large 3 (675B Instruct 2512)?

Key differences include LLM Stats Score (46.2 vs 9.0), context window (1.0M vs 262K), input pricing ($0.68 vs $0.50/M), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Related comparisons