All Releases•

35 models

Mistral Models: Intelligence, Performance & Price

Artificial Analysis has benchmarked 35 models from Mistral. Below is a comparison of the key metrics across these models.

  • For intelligence, the top model from Mistral is Mistral Large 4 (High) at 26.
  • For speed, Mistral Small 4 (Reasoning) at 1.6 min has the lowest time per task.
  • For latency, Ministral 3 3B at 1.54s offers the lowest time to first answer token.
  • For pricing, Mistral Small 4 (Reasoning) at $0.04 offers the lowest cost per task. Prices vary up to 52x across models.

IntelligenceUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

Intelligence Index vs. Cost per Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task
Most attractive quadrant
Pareto line

Cost

Cost per Intelligence Index Task

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

Speed & Latency

Time per Intelligence Index Task

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Speed at the model's own endpoint or the median across providers · Lower is better

Capability Scores

Capability Indexes

Measures the performance of models on specific capabilities and industries
Finance & Accounting Index

Incorporates 5 evaluations: AA-Briefcase v1.1, AA-Omniscience v1.1, HLE-Diamond, AutomationBench-AA, GDP.pdf · Higher is better

Strategy & Ops Index

Incorporates 4 evaluations: AutomationBench-AA, AA-Briefcase v1.1, AA-Omniscience v1.1, GDP.pdf · Higher is better

Legal Index

Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf, AutomationBench-AA · Higher is better

Healthcare & Medical Index

Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, MLCR-AA, AutomationBench-AA, HLE-Diamond · Higher is better

Engineering Index

Incorporates 7 evaluations: AA-Omniscience v1.1, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1, HLE-Diamond, Terminal-Bench 4.0, FrontierCode 2.0, AA-Briefcase v1.1 · Higher is better

Economics Index

Incorporates 4 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf · Higher is better

All Mistral Releases

Further details

Weights
Provider Benchmarks
Mistral Large 4 (High)
Mistral logoMistral
26
1.1T
52B active at inference time
1M
$0.4
14.1
97
Mistral
Mistral Large 4 Preview
Mistral logoMistral
25
1T
49B active at inference time
524k
$0.4
22.9
99
Not available
Mistral
Mistral Large 4 (Medium)
Mistral logoMistral
23
1.1T
52B active at inference time
1M
$0.4
10.2
92
Mistral
Mistral Medium 3.5
Mistral logoMistral
5
128B
256k
$1.2
4.8
137
Mistral
Mistral Small 4 (Reasoning)
Mistral logoMistral
4
119B
6.5B active at inference time
256k
$0.1
1.6
146
Mistral
Mistral Medium 3.1
Mistral logoMistral
-
-
128k
-
-
-
Not available
-
Devstral 2
Mistral logoMistral
-
125B
256k
-
-
-
-
Magistral Small 1
Mistral logoMistral
-
23.6B
40k
-
-
-
-
Mistral Small 4 (Non-reasoning)
Mistral logoMistral
-
119B
6.5B active at inference time
256k
$0.1
-
127
Mistral
Mistral Large 2 (Jul '24)
Mistral logoMistral
-
123B
128k
$2.4
-
-
Amazon Bedrock
Mistral Medium
Mistral logoMistral
-
-
33k
-
-
-
Not available
-
Mistral 7B Instruct
Mistral logoMistral
-
7B
8k
$0.2
-
100
Amazon Bedrock
Mistral Small 3.1
Mistral logoMistral
-
24B
128k
$0.1
-
63
DeepInfraMultiverse Computing
Mistral Small (Feb '24)
Mistral logoMistral
-
-
33k
-
-
-
Not available
-
Mixtral 8x7B Instruct
Mistral logoMistral
-
46.7B
12.9B active at inference time
33k
$0.5
-
64
Amazon Bedrock
Mistral Small 3.2
Mistral logoMistral
-
24B
128k
$0.1
-
34
DeepInfra
Mistral Large 3
Mistral logoMistral
-
675B
41B active at inference time
256k
$0.3
-
76
Amazon BedrockMicrosoft AzureMistral
Mistral Large 2 (Nov '24)
Mistral logoMistral
-
123B
128k
-
-
-
-
Mistral Medium 3
Mistral logoMistral
-
-
128k
$0.6
-
28
Not available
Microsoft Azure
Mistral Large (Feb '24)
Mistral logoMistral
-
-
33k
$4.8
-
-
Not available
Amazon Bedrock
Magistral Medium 1
Mistral logoMistral
-
-
40k
-
-
-
Not available
-
Ministral 3 3B
Mistral logoMistral
-
3B
256k
$0.0
-
114
Amazon BedrockMistral
Magistral Small 1.2
Mistral logoMistral
-
24B
128k
$0.6
-
69
Amazon Bedrock
Ministral 3 14B
Mistral logoMistral
-
14B
256k
$0.1
-
49
MistralAmazon BedrockDigitalOcean
Mistral Saba
Mistral logoMistral
-
24B
32k
-
-
-
Not available
-
Mistral Small (Sep '24)
Mistral logoMistral
-
22B
33k
-
-
-
-
Magistral Medium 1.2
Mistral logoMistral
-
-
128k
-
-
-
Not available
-
Ministral 3 8B
Mistral logoMistral
-
8B
256k
$0.1
-
65
Amazon BedrockMistral
Devstral Small (Jul '25)
Mistral logoMistral
-
24B
256k
-
-
-
-
Devstral Medium
Mistral logoMistral
-
-
256k
-
-
-
Not available
-
Mixtral 8x22B Instruct
Mistral logoMistral
-
141B
39B active at inference time
65k
-
-
-
-
Devstral Small (May '25)
Mistral logoMistral
-
23.6B
256k
-
-
-
-
Devstral Small 2
Mistral logoMistral
-
24B
256k
-
-
-
-
Pixtral Large
Mistral logoMistral
-
124B
128k
-
-
-
-
Mistral Small 3
Mistral logoMistral
-
24B
32k
$0.1
-
62
DeepInfra