Mistral Large 3 logo
Mistral
•

Open weights model

•

Released December 2025

Mistral Large 3の知能、性能、料金の分析

試す APIプロバイダーのベンチマーク

モデル概要

知能

16
Artificial Analysis Intelligence Index
知能は4段階中2です。

速度

42.9
1秒あたりの出力トークン数
速度は4段階中1です。

入力料金

$0.50
100万トークンあたりのUSD
入力料金は4段階中3です。

出力料金

$1.50
100万トークンあたりのUSD
出力料金は4段階中3です。

冗長性

5.6M
Intelligence Indexでの出力トークン数
冗長性は4段階中3です。

Mistral Large 3の知能は平均を下回ります。料金はやや高価です。これは同程度の規模の他の非推論オープンウェイトモデルと比較した場合です。 また、出力速度は特に遅く、回答はやや冗長です。 このモデルはテキスト、画像入力に対応し、テキストを出力します。コンテキストウィンドウは256kトークンです。

Mistral Large 3のArtificial Analysis Intelligence Indexスコアは16で、同等のモデルの中では平均以下です（中央値：17）。Intelligence Indexの評価では5.6Mトークンを生成し、中央値の4.8Mと比べてやや冗長でした。

Mistral Large 3の料金は入力100万トークンあたり$0.50（やや高価、中央値：$0.43）、出力100万トークンあたり$1.50（やや高価、中央値：$1.31）です。Intelligence IndexでMistral Large 3を評価するための総費用は$71.04でした。

Mistral Large 3の出力速度は毎秒43トークンで、特に遅い水準です（57）。

推論いいえ

このページでは、このモデルの非推論版を表示しています。

推論版も存在する可能性があります。

入力モダリティ

対応：テキスト、画像

出力モダリティ

対応：テキスト

コンテキストウィンドウ256k
Arial 12ポイントのA4用紙約384ページ分
総パラメーター数675B
有効パラメーター数41B
推論時にトークンごとに有効になるパラメーター数
ライセンスApache 2.0
モデルウェイトHugging Face

各指標は同じクラスのモデルと比較します。

  • 非推論モデル → 他の非推論モデルとのみ比較
  • 推論モデル → 推論モデルと非推論モデルの両方と比較
  • オープンウェイトモデル → 同じ規模クラスの他のオープンウェイトモデルとのみ比較：
    • 極小：パラメーター数≤4B
    • 小：パラメーター数4B～40B
    • 中：パラメーター数40B～150B
    • 大：パラメーター数>150B
  • 独自モデル → 入力／出力のブレンド料金を3:1として、同じ料金帯の独自モデルとオープンウェイトモデルを比較：
    • 100万トークンあたり<$0.15
    • 100万トークンあたり$0.15～$1
    • 100万トークンあたり>$1

ハイライト

知能

Artificial Analysis Intelligence Index · Higher is better

速度

Output tokens per second · Higher is better

タスクあたりの費用

Weighted average cost (USD) per Intelligence Index task · Lower is better

知能

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if the weights are available but commercial use is limited (typically requires obtaining a paid license).

ベンチマーク

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
GDPval-AA v2

Agentic real-world work tasks, (Elo-500)/2000

𝜏³-Banking

Agentic tool use

Terminal-Bench v2.1

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR

Long context reasoning

AA-Briefcase

Agentic knowledge work, Elo

AutomationBench-AA

Agentic SaaS workflows

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AANew

Agentic business operations

IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

Reasoning models are indicated by a lightbulb icon

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

AA-Omniscience

AA-Omniscience Index

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.
Reasoning models are indicated by a lightbulb icon

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.

Openness Index

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)
Reasoning models are indicated by a lightbulb icon

Intelligence Indexの比較

Intelligence Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task
Most attractive quadrant
Pareto line
Reasoning models are indicated by a lightbulb icon

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

トークン使用量

Output Tokens per Intelligence Index Task

Weighted average number of output tokens used to run one task in the Artificial Analysis Intelligence Index
Reasoning models are indicated by a lightbulb icon

The number of tokens required per Intelligence Index task. This is calculated by multiplying the output tokens per eval by the relative weights of each benchmark in the Intelligence Index, then dividing by task count (excluding repeats).

費用

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better
Reasoning models are indicated by a lightbulb icon

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index
Reasoning models are indicated by a lightbulb icon

The cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input, cache hit, cache write, reasoning, and answer token prices and the number of tokens used across evaluations (excluding repeats).

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens)
Reasoning models are indicated by a lightbulb icon

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

コンテキストウィンドウ

Context Window

Context window: tokens limit · Higher is better
Reasoning models are indicated by a lightbulb icon

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

速度

出力速度（1秒あたりのトークン数）で測定

Output Speed

Output tokens per second · Higher is better
Reasoning models are indicated by a lightbulb icon

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Time per Intelligence Index Task

Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better
Reasoning models are indicated by a lightbulb icon

The weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.

遅延

最初のトークンまでの時間（秒）で測定

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time
Reasoning models are indicated by a lightbulb icon

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

エンドツーエンド応答時間

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better
Reasoning models are indicated by a lightbulb icon

Seconds to receive a 500 token response. Key components:

  • Input time: Time to receive the first response token
  • Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
  • Answer time: Time to generate 500 output tokens, based on output speed

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

モデル規模（オープンウェイトモデルのみ）

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference
Reasoning models are indicated by a lightbulb icon

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

The number of parameters actually executed during each inference forward pass, expressed in billions. For Mixture of Experts (MoE) models, a routing mechanism selects a subset of experts per token, resulting in fewer active than total parameters. Dense models use all parameters, so active equals total.

よくある質問

Mistral Large 3に関するよくある質問

Mistral Large 3は2025年12月2日にリリースされました。

Mistral Large 3はMistralが開発しました。

Mistral Large 3のArtificial Analysis Intelligence Indexスコアは16で、同程度の規模の他の非推論オープンウェイトモデルの中では平均以下水準です（中央値：17）。

Mistral Large 3の出力速度は毎秒42.9トークンです（MistralのAPIに基づく）。同程度の規模の他の非推論オープンウェイトモデルと比べて平均以下水準です（中央値：57.0 t/s）。

Mistral Large 3の最初のトークンまでの時間（TTFT）は1.29秒です（MistralのAPIに基づく）。同程度の規模の他の非推論オープンウェイトモデルと比べて非常に優れている水準です（中央値：1.84秒）。

Mistral Large 3の料金は入力100万トークンあたり$0.50（平均より安い、中央値：$0.60）、出力100万トークンあたり$1.50（平均より安い、中央値：$2.50）です。MistralのAPIに基づきます。

Mistral Large 3の料金は入力100万トークンあたり$0.50、出力100万トークンあたり$1.50です（MistralのAPIに基づく）。キャッシュヒット／入力／出力を7:2:1とするブレンド料金は、100万トークンあたり$0.60です。料金はプロバイダーによって異なる場合があります。 プロバイダー料金を比較

Intelligence Indexの評価で、Mistral Large 3は5.6M出力トークンを生成しました。同程度の規模の他の非推論オープンウェイトモデルと比べて平均よりやや多い水準です（中央値：4.8M）。

いいえ。Mistral Large 3は推論モデルではありません。思考の連鎖による長い推論を行わず、直接回答します。

Mistral Large 3はテキスト、画像入力に対応しています。

Mistral Large 3はテキスト出力に対応しています。

はい。Mistral Large 3は画像入力に対応し、画像の分析、説明、画像に関する質問への回答が可能です。

はい。Mistral Large 3はマルチモーダルです。テキスト、画像入力を処理し、テキスト出力を生成できます。

Mistral Large 3のコンテキストウィンドウは260kトークンです。これは、モデルが1回のリクエストで処理できるテキストと会話履歴の量を決定します。

はい。Mistral Large 3はオープンウェイトモデルです。モデルウェイトが一般公開されており、ダウンロードしてセルフホストできます。

Mistral Large 3のパラメーター数は675Bで、そのうち41Bが有効です。

Mistral Large 3は総パラメーター数675BのMixture of Experts（MoE）モデルですが、推論時に使用する有効パラメーター数は41Bのみです。

Mistral Large 3はApache 2.0ライセンスで公開されており、商用利用が認められています。 ライセンスを表示

Mistral Large 3のArtificial Analysis Intelligence Indexスコアは16です。この複合ベンチマークでは、推論、知識、数学、コーディングについてモデルを評価します。

はい。Mistral Large 3は3社のプロバイダーを通じてAPIで利用できます。 APIプロバイダーを比較

Mistral Large 3は3社のAPIプロバイダーを通じて利用できます。 プロバイダーを比較