32個のモデル

Mistralのモデル：知能・性能・料金

Name: Artificial Analysis Intelligence Index
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

Mistral

知能

Mistral Small 4 (Non-reasoning)

Artificial Analysis Intelligence Index

* 推定値

速度

Mistral Small 4 (Non-reasoning)

160 トークン/秒

Ministral 3 8B

104 トークン/秒

出力速度

費用

Intelligence Indexのタスクあたり

Artificial AnalysisはMistralの32個のモデルをベンチマークしています。以下では、これらのモデルの主要指標を比較します。

知能が最も高いMistralのモデルはMistral Medium 3.5（14）です。
出力速度が最も速いモデルはMinistral 3 3B（210トークン/秒）です。
最初の回答トークンまでの時間が最も短いモデルはMinistral 3 8B（0.74秒）です。
タスクあたりの費用が最も低いモデルはMinistral 3 3B（$0.01）です。モデル間の料金差は最大64倍です。

知能

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Estimate (independent evaluation forthcoming)

Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

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

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.

費用

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better

速度と遅延

Output Speed

Output tokens per second · Higher is better

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 or the median across providers where a first-party API is not available.

能力スコア

能力指数

特定の能力や業界におけるモデルの性能を測定

Finance & Accounting Index

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Strategy & Ops Index

Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Legal Index

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better

Healthcare & Medical Index

Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better

Engineering Index

Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better

Economics Index

Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · Higher is better

Mistralのすべてのリリース

詳細

							ウェイト		プロバイダーのベンチマーク
Mistral Medium 3.5	Mistral	14	128B	256k	$1.2	167	🤗		表示
Magistral Medium 1.2	Mistral	12	-	128k	-	-	利用不可	-	表示
Mistral Small 4 (Reasoning)	Mistral	11	119B 推論時に6.5Bが有効	256k	$0.1	181	🤗		表示
Mistral Large 3	Mistral	9	675B 推論時に41Bが有効	256k	$0.3	79	🤗		表示
Mistral Medium 3.1	Mistral	9	-	128k	-	-	利用不可	-	表示
Magistral Medium 1	Mistral	9	-	40k	-	-	利用不可	-	表示
Mistral Medium 3	Mistral	9	-	128k	$0.6	-	利用不可		表示
Devstral Medium	Mistral	9	-	256k	-	-	利用不可	-	表示
Mistral Small 4 (Non-reasoning)	Mistral	9	119B 推論時に6.5Bが有効	256k	$0.1	160	🤗		表示
Devstral Small (May '25)	Mistral	9	23.6B	256k	-	-	🤗	-	表示
Devstral 2	Mistral	9	125B	256k	-	-	🤗	-	表示
Magistral Small 1.2	Mistral	9	24B	128k	$0.6	-	🤗		表示
Mistral Small 3.2	Mistral	8	24B	128k	$0.1	-	🤗		表示
Magistral Small 1	Mistral	8	23.6B	40k	-	-	🤗	-	表示
Devstral Small (Jul '25)	Mistral	8	24B	256k	-	-	🤗	-	表示
Mistral Large 2 (Nov '24)	Mistral	8	123B	128k	-	-	🤗	-	表示
Devstral Small 2	Mistral	8	24B	256k	-	-	🤗	-	表示
Pixtral Large	Mistral	7	124B	128k	-	-	🤗	-	表示
Mistral Small 3.1	Mistral	7	24B	128k	$0.1	-	🤗		表示
Mistral Large 2 (Jul '24)	Mistral	7	123B	128k	$2.4	-	🤗		表示
Mistral Small 3	Mistral	7	24B	32k	$0.1	-	🤗		表示
Mistral Saba	Mistral	6	24B	32k	-	-	利用不可	-	表示
Ministral 3 14B	Mistral	6	14B	256k	$0.1	87	🤗		表示
Mistral Small (Sep '24)	Mistral	6	22B	33k	-	-	🤗	-	表示
Mistral Large (Feb '24)	Mistral	6	-	33k	$4.8	-	利用不可		表示
Mixtral 8x22B Instruct	Mistral	6	141B 推論時に39Bが有効	65k	-	-	🤗	-	表示
Mistral Small (Feb '24)	Mistral	6	-	33k	-	-	利用不可	-	表示
Mistral Medium	Mistral	5	-	33k	-	-	利用不可	-	表示
Ministral 3 8B	Mistral	5	8B	256k	$0.1	104	🤗		表示
Mixtral 8x7B Instruct	Mistral	5	46.7B 推論時に12.9Bが有効	33k	$0.5	-	🤗		表示
Mistral 7B Instruct	Mistral	5	7B	8k	$0.2	-	🤗		表示
Ministral 3 3B	Mistral	5	3B	256k	$0.0	210	🤗		表示

Mistralのモデル：知能・性能・料金

知能

速度

費用

知能

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Index vs. Cost per Intelligence Index Task

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

費用

Cost per Intelligence Index Task

Cost per Intelligence Index Task

速度と遅延

Output Speed

Output Speed

Model Performance Representation

能力スコア

能力指数

Mistralのすべてのリリース

詳細