Skip to content

Listings

All listings: Mistral AI

Every listing for the models on page 2 of 4 of Mistral AI, including each model's other versions and routes. Back to Mistral AI

Sold by Mistral AI

34 listings on this page sold by Mistral AI.

Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Modelllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueYapEpoch Capabilities Index
Mistral Large
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±9
Coding IQ 72.2, 95% interval 63–81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00$6.00Not published by the provider
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral-large-latest Β· latest
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±9
Coding IQ 72.2, 95% interval 63–81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.70cache read $0.07$2.101M
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.14cache read $0.01$0.4232K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral-small-2603 Β· 2603
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.60262K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral-small-latest Β· latest
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10cache read $0.015$0.30262K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral-small-2506 Β· 2506
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10$0.30128K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Ministral 8B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
107.6
From 73 benchmarks. Plenty of data behind it.
Not enough data yet$0.10$1.00Not published by the provider
54.6
Good value (54.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 8B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
ministral-8b-2512 Β· 2512
107.6
From 73 benchmarks. Plenty of data behind it.
Not enough data yet$0.15cache read $0.015$0.15262K
54.6
Good value (54.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 8B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
ministral-8b-latest Β· latest
107.6
From 73 benchmarks. Plenty of data behind it.
Not enough data yet$0.15cache read $0.015$0.15262K
54.6
Good value (54.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Mixtral 8x22B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
107.4
From 7 benchmarks. A fair amount of data behind it.
Not enough data yet$0.90$0.90Not published by the providerNot enough data yetNot measuredNot measured
Mistral Small 24B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral-small-24b-instruct-2501 Β· 2501
106.3
From 74 benchmarks. Plenty of data behind it.
β‰ˆ 78Β Β±11
Coding IQ 77.9, 95% interval 67–89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.05$0.08Not published by the providerNot enough data yetNot measuredNot measured
open-mistral-7b
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
β‰ˆ 106
From 5 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.25$0.25Not published by the providerNot enough data yetNot measuredNot measured
Ministral 3 14B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/ministral-3-14b-2512 Β· 2512
β‰ˆ 103
From 32 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.20cache read $0.02$0.20262KNot enough data yetNot measuredNot measured
codestral-mamba
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/codestral-mamba-latest Β· latest
β‰ˆ 102
From 4 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.25cache read $0.025$0.25256KNot enough data yetNot measuredNot measured
Ministral 3B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
100.6
From 24 benchmarks. Plenty of data behind it.
Not enough data yet$0.04$0.04Not published by the provider
38.6
Poor value (38.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 3B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
ministral-3b-2512 Β· 2512
100.6
From 24 benchmarks. Plenty of data behind it.
Not enough data yet$0.10cache read $0.01$0.10262K
38.6
Poor value (38.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 3B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
ministral-3b-latest Β· latest
100.6
From 24 benchmarks. Plenty of data behind it.
Not enough data yet$0.10cache read $0.01$0.10262K
38.6
Poor value (38.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 3 8B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/ministral-3-8b-2512 Β· 2512
β‰ˆ 100
From 32 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.15cache read $0.015$0.15262KNot enough data yetNot measuredNot measured
Mistral Nemo
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
98.1
From 85 benchmarks. Plenty of data behind it.
Not enough data yet$0.15$0.15Not published by the provider
52.2
Fair value (52.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
113.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Pixtral 12B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
96.6
From 81 benchmarks. Plenty of data behind it.
Not enough data yet$0.15$0.15128K
54.4
Good value (54.4). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Open Mistral Nemo
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
β‰ˆ 96
From 78 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.30cache read $0.03$0.30128KNot enough data yetNot measuredNot measured
Mistral 7B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
β‰ˆ 95
From 32 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.14$0.42Not published by the provider
60.8
Good value (60.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 3 3B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/ministral-3-3b-2512 Β· 2512
β‰ˆ 94
From 32 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.10cache read $0.01$0.10131KNot enough data yetNot measuredNot measured
mistral-7b
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
β‰ˆ 91
From 4 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.25$0.25Not published by the providerNot enough data yetNot measuredNot measured
Mistral 7B Instruct v0.2
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
88.3
From 144 benchmarks. Plenty of data behind it.
β‰ˆ 76Β Β±12
Coding IQ 75.7, 95% interval 64–88. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.14$0.42Not published by the provider
46.7
Poor value (46.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Mistral (7B) Instruct v0.1
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
87.1
From 34 benchmarks. Plenty of data behind it.
Not enough data yet$0.14$0.42Not published by the provider
39.4
Poor value (39.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Mistral (7B) Instruct v0.3
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
85.5
From 276 benchmarks. Plenty of data behind it.
Not enough data yet$0.14$0.42Not published by the provider
47.1
Poor value (47.1). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Mistral Embed
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.10cache read $0.01β€”8KNot enough data yetNot measuredNot measured
Voxtral Small 24B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
voxtral-small-24b-2507 Β· 2507
Not enough data yetNot enough data yet$0.10cache read $0.01$0.30Not published by the provider
51.5
Fair value (51.5). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Voxtral Small Transcribe
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
voxtral-small-2507
Not enough data yetNot enough data yet$0.10cache read $0.01$0.4033KNot enough data yetNot measuredNot measured
Voxtral Small (latest)
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Not enough data yetNot enough data yet$0.10cache read $0.01$0.4033KNot enough data yetNot measuredNot measured
Mixtral 8x7B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.14$0.42Not published by the provider
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Codestral Embed
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.15cache read $0.015β€”8KNot enough data yetNot measuredNot measured
Codestral Embed
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
codestral-embed-2505 Β· 2505
Not enough data yetNot enough data yet$0.15cache read $0.015β€”8KNot enough data yetNot measuredNot measured

Run by Mistral AI

44 listings on this page where Mistral AI runs the model. Another provider sells these listings.

Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
ModelProviderllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueYapEpoch Capabilities Index
Mistral Large
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/mistral-large-2407 Β· 2407
Β Eden AI
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±9
Coding IQ 72.2, 95% interval 63–81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$6.00131K
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/mistral-large-2407@eu Β· 2407 Β· πŸ‡ͺπŸ‡Ί eu
Β Eden AI
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±9
Coding IQ 72.2, 95% interval 63–81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$6.60131K
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/mistral-large-latest@eu Β· latest Β· πŸ‡ͺπŸ‡Ί eu
Β Eden AI
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±9
Coding IQ 72.2, 95% interval 63–81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$6.601M
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/mistral-large-latest Β· latest
Β Eden AI
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±9
Coding IQ 72.2, 95% interval 63–81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$6.001M
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral-large-latest Β· latest
Β Llmgateway
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±9
Coding IQ 72.2, 95% interval 63–81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00$12.00Not published by the provider
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Β OpenRouter
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±9
Coding IQ 72.2, 95% interval 63–81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$6.00128K
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistralai/mistral-large-2407 Β· 2407
Β OpenRouter
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±9
Coding IQ 72.2, 95% interval 63–81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$6.00131K
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistralai/mistral-large-2407 Β· eu+2407
Β OpenRouter
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±9
Coding IQ 72.2, 95% interval 63–81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$6.60131K
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistralai/mistral-large-2407 Β· zdr+2407
Β OpenRouter
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±9
Coding IQ 72.2, 95% interval 63–81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$6.00131K
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/mistral-large-latest Β· latest
Β Requesty
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±9
Coding IQ 72.2, 95% interval 63–81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.55$1.65131K
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral-small-2603 Β· 2603
Β Cortecs AI
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”262K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral/mistral-small-2603 Β· 2603
Β Eden AI
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.60262K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral/mistral-small-2603@eu Β· 2603 Β· πŸ‡ͺπŸ‡Ί eu
Β Eden AI
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.165cache read $0.0165$0.66262K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral/mistral-small-latest@eu Β· latest Β· πŸ‡ͺπŸ‡Ί eu
Β Eden AI
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.165cache read $0.0165$0.66262K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral/mistral-small-latest Β· latest
Β Eden AI
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.60262K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral-small-2506 Β· 2506
Β Llmgateway
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10$0.30Not published by the provider
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral-small-2603 Β· 2603
Β Llmgateway
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15$0.60Not published by the provider
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/mistral-small-2603 Β· eu+2603
Β OpenRouter
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.165cache read $0.0165$0.66262K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/mistral-small-2603 Β· us+2603
Β OpenRouter
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.165cache read $0.0165$0.66262K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/mistral-small-2603 Β· zdr+2603
Β OpenRouter
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.60262K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral/mistral-small-2503 Β· 2503
Β Requesty
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.11$0.3333K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral/mistral-small-2603 Β· 2603
Β Requesty
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.165$0.66256K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral/mistral-small-latest Β· latest
Β Requesty
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.165$0.66256K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Ministral 8B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
ministral-8b-2512 Β· 2512
Β Cortecs AI
107.6
From 73 benchmarks. Plenty of data behind it.
Not enough data yetβ€”β€”256K
54.6
Good value (54.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 8B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral/ministral-8b-2512 Β· 2512
Β Eden AI
107.6
From 73 benchmarks. Plenty of data behind it.
Not enough data yet$0.15cache read $0.015$0.15262K
54.6
Good value (54.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 8B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral/ministral-8b-2512@eu Β· 2512 Β· πŸ‡ͺπŸ‡Ί eu
Β Eden AI
107.6
From 73 benchmarks. Plenty of data behind it.
Not enough data yet$0.165cache read $0.0165$0.165262K
54.6
Good value (54.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 8B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
ministral-8b-2512 Β· 2512
Β Llmgateway
107.6
From 73 benchmarks. Plenty of data behind it.
Not enough data yet$0.15$0.15Not published by the provider
54.6
Good value (54.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 8B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/ministral-8b-2512 Β· eu+2512
Β OpenRouter
107.6
From 73 benchmarks. Plenty of data behind it.
Not enough data yet$0.165cache read $0.0165$0.165262K
54.6
Good value (54.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 8B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/ministral-8b-2512 Β· zdr+2512
Β OpenRouter
107.6
From 73 benchmarks. Plenty of data behind it.
Not enough data yet$0.15cache read $0.015$0.15262K
54.6
Good value (54.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Mixtral 8x22B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
eu
Β OpenRouter
107.4
From 7 benchmarks. A fair amount of data behind it.
Not enough data yet$2.20cache read $0.22$6.6066KNot enough data yetNot measuredNot measured
Mixtral 8x22B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
zdr
Β OpenRouter
107.4
From 7 benchmarks. A fair amount of data behind it.
Not enough data yet$2.00cache read $0.20$6.0066KNot enough data yetNot measuredNot measured
open-mistral-7b
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Β Requesty
β‰ˆ 106
From 5 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.275$0.27533KNot enough data yetNot measuredNot measured
Ministral 3B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
ministral-3b-2512 Β· 2512
Β Cortecs AI
100.6
From 24 benchmarks. Plenty of data behind it.
Not enough data yetβ€”β€”256K
38.6
Poor value (38.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 3B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral/ministral-3b-2512 Β· 2512
Β Eden AI
100.6
From 24 benchmarks. Plenty of data behind it.
Not enough data yet$0.10cache read $0.01$0.10131K
38.6
Poor value (38.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 3B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral/ministral-3b-2512@eu Β· 2512 Β· πŸ‡ͺπŸ‡Ί eu
Β Eden AI
100.6
From 24 benchmarks. Plenty of data behind it.
Not enough data yet$0.11cache read $0.011$0.11131K
38.6
Poor value (38.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 3B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
ministral-3b-2512 Β· 2512
Β Llmgateway
100.6
From 24 benchmarks. Plenty of data behind it.
Not enough data yet$0.10$0.10Not published by the provider
38.6
Poor value (38.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 3B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/ministral-3b-2512 Β· eu+2512
Β OpenRouter
100.6
From 24 benchmarks. Plenty of data behind it.
Not enough data yet$0.11cache read $0.011$0.11131K
38.6
Poor value (38.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ministral 3B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/ministral-3b-2512 Β· zdr+2512
Β OpenRouter
100.6
From 24 benchmarks. Plenty of data behind it.
Not enough data yet$0.10cache read $0.01$0.10131K
38.6
Poor value (38.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Mistral Nemo
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
eu
Β OpenRouter
98.1
From 85 benchmarks. Plenty of data behind it.
Not enough data yet$0.15cache read $0.015$0.15131K
52.2
Fair value (52.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
113.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Voxtral Small 24B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/voxtral-small-24b-2507 Β· eu+2507
Β OpenRouterNot enough data yetNot enough data yet$0.11cache read $0.011$0.3332K
51.5
Fair value (51.5). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Voxtral Small 24B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/voxtral-small-24b-2507 Β· zdr+2507
Β OpenRouterNot enough data yetNot enough data yet$0.10cache read $0.01$0.3033K
51.5
Fair value (51.5). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Voxtral Small Transcribe
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
voxtral-small-2507
Β Cortecs AINot enough data yetNot enough data yetβ€”β€”32KNot enough data yetNot measuredNot measured
Voxtral Small (latest)
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Β Eden AINot enough data yetNot enough data yet$0.10cache read $0.01$0.4033KNot enough data yetNot measuredNot measured
Voxtral Small (latest)
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistral/voxtral-small-latest@eu Β· πŸ‡ͺπŸ‡Ί eu
Β Eden AINot enough data yetNot enough data yet$0.11cache read $0.011$0.4433KNot enough data yetNot measuredNot measured

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

How this data works