Skip to content

Listings

All listings: Mistral AI

Every listing for the models on page 1 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
DeepSeek V4.1 Flash 1017
🇨🇳
Maker headquartered in CN, 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.
139.7
From 97 benchmarks. Plenty of data behind it.
127 ±8
Coding IQ 126.8, 95% interval 119–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.30cache read $0.007$1.201M
71.4
Good value (71.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
55 ±9
Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
159.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3
🇨🇳
Maker headquartered in CN, 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/zai-glm-5-3
138.2
From 318 benchmarks. Plenty of data behind it.
121 ±9
Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40cache read $0.14$4.401M
57.7
Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±10
Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
157.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGLM 5.3We compared release dates and version names in our catalogue.
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40cache read $0.14$4.401M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
Maker headquartered in CN, 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/zai-glm-5-3-flash
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.03$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGLM 5.3We compared release dates and version names in our catalogue.
mistral/zai-glm-5
129.7
From 306 benchmarks. Plenty of data behind it.
107 ±5
Coding IQ 106.7, 95% interval 102–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40cache read $0.14$4.401M
49.7
Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
55 ±9
Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
146.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large 4
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
129.6
From 173 benchmarks. Plenty of data behind it.
115 ±7
Coding IQ 114.7, 95% interval 108–122. Plenty 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
30.8
Poor value (30.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
62 ±9
Chatty (62 ±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.
154.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Devstral 2 123b Instruct 2512
🇫🇷
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.
devstral-2512
119.5
From 25 benchmarks. Plenty of data behind it.
97 ±9
Coding IQ 97.1, 95% interval 88–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.40cache read $0.04$2.00262K
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Mistral Medium 3.1
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral-medium-2508
118.5
From 23 benchmarks. Plenty of data behind it.
Not enough data yet$0.40$2.00262K
50.3
Fair value (50.3). Costs per task about what its benchmark results predict. A fair amount of data behind it.
42 ±9
Terse (42 ±9). Generates fewer 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 Large 3
🇫🇷
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-large-2512
118.1
From 60 benchmarks. Plenty of data behind it.
86 ±8
Coding IQ 86.4, 95% interval 79–94. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.50cache read $0.05$1.50262K
38.5
Poor value (38.5). Costs more per task than its benchmark results predict. Plenty of data behind it.
40 ±9
Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Devstral Medium
🇫🇷
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.
≈ 117
From 10 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet——Not published by the provider
42.0
Poor value (42.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Devstral Medium
🇫🇷
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/devstral-medium-latest · latest
≈ 117
From 10 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.40cache read $0.04$2.00256K
42.0
Poor value (42.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Codestral 25.01
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
codestral
116.6
From 10 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$0.90Not published by the provider
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. A fair amount of data behind it.
40 ±9
Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Codestral 25.01
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
codestral-2508 · 2508
116.6
From 10 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30cache read $0.03$0.90128K
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. A fair amount of data behind it.
40 ±9
Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Codestral 25.01
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
codestral-latest · latest
116.6
From 10 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30cache read $0.03$0.90128K
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. A fair amount of data behind it.
40 ±9
Terse (40 ±9). Generates fewer 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 Large 3
🇫🇷
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.
Newer version
Newer versionMistral Large 4We compared release dates and version names in our catalogue.
116.5
From 105 benchmarks. Plenty of data behind it.
Not enough data yet$0.50cache read $0.05$1.50262K
56.3
Good value (56.3). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Mistral Medium 3
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Newer version
Newer versionMistral Medium 3.5We compared release dates and version names in our catalogue.
116.4
From 50 benchmarks. A fair amount of data behind it.
Not enough data yet$0.40cache read $0.15$2.00262K
51.0
Fair value (51.0). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
132.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Ministral 14B
🇫🇷
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-14b-2512 · 2512
115.6
From 33 benchmarks. A fair amount of data behind it.
Not enough data yet$0.20cache read $0.02$0.20262KNot enough data yetNot measuredNot measured
Ministral 14B
🇫🇷
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-14b-latest · latest
115.6
From 33 benchmarks. A fair amount of data behind it.
Not enough data yet$0.20cache read $0.02$0.20262KNot enough data yetNot measuredNot measured
Mistral Medium 3.5
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
115.3
From 173 benchmarks. Plenty of data behind it.
99 ±15
Coding IQ 98.6, 95% interval 84–114. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.50cache read $0.15$7.50262K
12.0
Poor value (12.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
141.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Medium
🇫🇷
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.
114.7
From 48 benchmarks. Plenty of data behind it.
≈ 91 ±14
Coding IQ 90.8, 95% interval 76–105. 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.
$2.39cache read $0.15$7.17262K
24.3
Poor value (24.3). Costs more per task than its benchmark results predict. A fair amount of data behind it.
59 ±9
Chatty (59 ±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 Medium
🇫🇷
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-medium-2604 · 2604
114.7
From 48 benchmarks. Plenty of data behind it.
≈ 91 ±14
Coding IQ 90.8, 95% interval 76–105. 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.
$1.50cache read $0.15$7.50262K
24.3
Poor value (24.3). Costs more per task than its benchmark results predict. A fair amount of data behind it.
59 ±9
Chatty (59 ±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 Medium
🇫🇷
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-medium-latest · latest
114.7
From 48 benchmarks. Plenty of data behind it.
≈ 91 ±14
Coding IQ 90.8, 95% interval 76–105. 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.
$2.39cache read $0.15$7.17262K
24.3
Poor value (24.3). Costs more per task than its benchmark results predict. A fair amount of data behind it.
59 ±9
Chatty (59 ±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
Pixtral Large
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
114.2
From 15 benchmarks. Plenty of data behind it.
Not enough data yet$2.00$6.00Not published by the provider
44.0
Poor value (44.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Pixtral Large
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/pixtral-large-latest · latest
114.2
From 15 benchmarks. Plenty of data behind it.
Not enough data yet$2.00cache read $0.20$6.00128K
44.0
Poor value (44.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Mistral Small 3.2
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
≈ 114
From 44 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$100.00$300.00Not published by the providerNot enough data yetNot measuredNot measured
Mistral Small 3.2 24B Instruct
🇫🇷
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.
113.3
From 50 benchmarks. Plenty of data behind it.
Not enough data yet$0.075$0.20Not published by the provider
58.5
Good value (58.5). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Mistral Medium 3
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral-medium-2505
113.0
From 33 benchmarks. Plenty of data behind it.
Not enough data yet$0.40$2.00131K
42.0
Poor value (42.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
Devstral Small 2505
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
devstral-small
112.7
From 14 benchmarks. A fair amount of data behind it.
≈ 83 ±10stale
Coding IQ 82.9, 95% interval 73–93. 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. Its newest result is over a year old.
$0.06$0.12Not published by the provider
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Devstral Small 2505
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/devstral-small-latest · latest
112.7
From 14 benchmarks. A fair amount of data behind it.
≈ 83 ±10stale
Coding IQ 82.9, 95% interval 73–93. 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. Its newest result is over a year old.
$0.10cache read $0.01$0.30256K
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Magistral Medium
🇫🇷
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.
112.6
From 69 benchmarks. Plenty of data behind it.
92 ±10
Coding IQ 91.6, 95% interval 82–101. 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$5.00Not published by the provider
22.3
Poor value (22.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
Magistral Medium
🇫🇷
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.
magistral-medium-latest · latest
112.6
From 69 benchmarks. Plenty of data behind it.
92 ±10
Coding IQ 91.6, 95% interval 82–101. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.50cache read $0.15$7.50262K
22.3
Poor value (22.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
Magistral Small 2509
🇫🇷
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.
magistral-small
109.2
From 42 benchmarks. Plenty of data behind it.
Not enough data yet$0.50$1.50Not published by the provider
27.6
Poor value (27.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
Magistral Small 2509
🇫🇷
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.
magistral-small-latest · latest
109.2
From 42 benchmarks. Plenty of data behind it.
Not enough data yet$0.15cache read $0.015$0.60262K
27.6
Poor value (27.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
open-mixtral-8x7b
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
≈ 109
From 5 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.70$0.70Not published by the providerNot enough data yetNot measuredNot measured

Run by Mistral AI

66 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
DeepSeek V4.1 Flash 1017
🇨🇳
Maker headquartered in CN, 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.
 Hugging Face
139.7
From 97 benchmarks. Plenty of data behind it.
127 ±8
Coding IQ 126.8, 95% interval 119–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.30$1.201M
71.4
Good value (71.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
55 ±9
Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
159.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4.1 Flash 1017
🇨🇳
Maker headquartered in CN, 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.
 Llmgateway
139.7
From 97 benchmarks. Plenty of data behind it.
127 ±8
Coding IQ 126.8, 95% interval 119–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.30cache read $0.007$1.20Not published by the provider
71.4
Good value (71.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
55 ±9
Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
159.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4.1 Flash 1017
🇨🇳
Maker headquartered in CN, 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.
latest
 Llmgateway
139.7
From 97 benchmarks. Plenty of data behind it.
127 ±8
Coding IQ 126.8, 95% interval 119–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.30cache read $0.007$1.20Not published by the provider
71.4
Good value (71.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
55 ±9
Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
159.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4.1 Flash 1017
🇨🇳
Maker headquartered in CN, 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.
fp8
 OpenRouter
139.7
From 97 benchmarks. Plenty of data behind it.
127 ±8
Coding IQ 126.8, 95% interval 119–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.30cache read $0.007$1.201M
71.4
Good value (71.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
55 ±9
Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
159.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3
🇨🇳
Maker headquartered in CN, 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.
 Cortecs AI
138.2
From 318 benchmarks. Plenty of data behind it.
121 ±9
Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——1M
57.7
Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±10
Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
157.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3
🇨🇳
Maker headquartered in CN, 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.
 Hugging Face
138.2
From 318 benchmarks. Plenty of data behind it.
121 ±9
Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40$4.401M
57.7
Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±10
Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
157.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3
🇨🇳
Maker headquartered in CN, 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.
zai-glm-5-3
 Llmgateway
138.2
From 318 benchmarks. Plenty of data behind it.
121 ±9
Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40cache read $0.14$4.40Not published by the provider
57.7
Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±10
Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
157.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3
🇨🇳
Maker headquartered in CN, 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.
nvfp4/eu · nvfp4
 OpenRouter
138.2
From 318 benchmarks. Plenty of data behind it.
121 ±9
Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.54cache read $0.154$4.841M
57.7
Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±10
Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
157.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3
🇨🇳
Maker headquartered in CN, 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 · nvfp4
 OpenRouter
138.2
From 318 benchmarks. Plenty of data behind it.
121 ±9
Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40cache read $0.14$4.401M
57.7
Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±10
Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
157.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGLM 5.3We compared release dates and version names in our catalogue.
 Hugging Face
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40$4.401M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGLM 5.3We compared release dates and version names in our catalogue.
eu
 OpenRouter
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.54cache read $0.154$4.841M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGLM 5.3We compared release dates and version names in our catalogue.
zdr
 OpenRouter
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40cache read $0.14$4.401M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
Maker headquartered in CN, 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.
 Cortecs AI
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——1M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
Maker headquartered in CN, 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.
 Hugging Face
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
Maker headquartered in CN, 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.
zai-glm-5-3-flash
 Llmgateway
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.03$0.50Not published by the provider
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
Maker headquartered in CN, 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.
 OpenRouter
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.03$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large 4
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral-large-4-0
 Cortecs AI
129.6
From 173 benchmarks. Plenty of data behind it.
115 ±7
Coding IQ 114.7, 95% interval 108–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——1M
30.8
Poor value (30.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
62 ±9
Chatty (62 ±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.
154.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large 4
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/mistral-large-4@eu · 🇪🇺 eu
 Eden AI
129.6
From 173 benchmarks. Plenty of data behind it.
115 ±7
Coding IQ 114.7, 95% interval 108–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.748cache read $0.077$2.299524K
30.8
Poor value (30.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
62 ±9
Chatty (62 ±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.
154.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large 4
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral-large-4-0
 Llmgateway
129.6
From 173 benchmarks. Plenty of data behind it.
115 ±7
Coding IQ 114.7, 95% interval 108–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.36cache read $0.14$4.18Not published by the provider
30.8
Poor value (30.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
62 ±9
Chatty (62 ±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.
154.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large 4
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistralai/mistral-large-4-0 · eu
 OpenRouter
129.6
From 173 benchmarks. Plenty of data behind it.
115 ±7
Coding IQ 114.7, 95% interval 108–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.77cache read $0.077$2.31524K
30.8
Poor value (30.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
62 ±9
Chatty (62 ±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.
154.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large 4
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistralai/mistral-large-4-0 · zdr
 OpenRouter
129.6
From 173 benchmarks. Plenty of data behind it.
115 ±7
Coding IQ 114.7, 95% interval 108–122. Plenty 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
30.8
Poor value (30.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
62 ±9
Chatty (62 ±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.
154.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Medium 3.1
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Newer version
Newer versionMistral Medium 3.5We compared the version names in our catalogue.
eu
 OpenRouter
119.6
From 89 benchmarks. Plenty of data behind it.
Not enough data yet$0.44cache read $0.044$2.20131KNot enough data yetNot measuredNot measured
Devstral 2 123b Instruct 2512
🇫🇷
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/devstral-2512
 Eden AI
119.5
From 25 benchmarks. Plenty of data behind it.
97 ±9
Coding IQ 97.1, 95% interval 88–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.40cache read $0.04$2.00262K
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Devstral 2 123b Instruct 2512
🇫🇷
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/devstral-2512@eu · 🇪🇺 eu
 Eden AI
119.5
From 25 benchmarks. Plenty of data behind it.
97 ±9
Coding IQ 97.1, 95% interval 88–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.44cache read $0.044$2.20262K
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Devstral 2 123b Instruct 2512
🇫🇷
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.
devstral-2512
 Llmgateway
119.5
From 25 benchmarks. Plenty of data behind it.
97 ±9
Coding IQ 97.1, 95% interval 88–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.40$2.00Not published by the provider
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Devstral 2 123b Instruct 2512
🇫🇷
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/devstral-2512 · eu
 OpenRouter
119.5
From 25 benchmarks. Plenty of data behind it.
97 ±9
Coding IQ 97.1, 95% interval 88–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.40cache read $0.04$2.00262K
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Mistral Large 3
🇫🇷
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-large-2512
 Eden AI
118.1
From 60 benchmarks. Plenty of data behind it.
86 ±8
Coding IQ 86.4, 95% interval 79–94. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.50cache read $0.05$1.50262K
38.5
Poor value (38.5). Costs more per task than its benchmark results predict. Plenty of data behind it.
40 ±9
Terse (40 ±9). Generates fewer 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 Large 3
🇫🇷
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-large-2512@eu · 🇪🇺 eu
 Eden AI
118.1
From 60 benchmarks. Plenty of data behind it.
86 ±8
Coding IQ 86.4, 95% interval 79–94. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.55cache read $0.055$1.65262K
38.5
Poor value (38.5). Costs more per task than its benchmark results predict. Plenty of data behind it.
40 ±9
Terse (40 ±9). Generates fewer 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 Large 3
🇫🇷
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-large-2512
 Llmgateway
118.1
From 60 benchmarks. Plenty of data behind it.
86 ±8
Coding IQ 86.4, 95% interval 79–94. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.50$1.50Not published by the provider
38.5
Poor value (38.5). Costs more per task than its benchmark results predict. Plenty of data behind it.
40 ±9
Terse (40 ±9). Generates fewer 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 Large 3
🇫🇷
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-large-2512 · eu
 OpenRouter
118.1
From 60 benchmarks. Plenty of data behind it.
86 ±8
Coding IQ 86.4, 95% interval 79–94. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.55cache read $0.055$1.65262K
38.5
Poor value (38.5). Costs more per task than its benchmark results predict. Plenty of data behind it.
40 ±9
Terse (40 ±9). Generates fewer 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 Large 3
🇫🇷
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-large-2512 · zdr
 OpenRouter
118.1
From 60 benchmarks. Plenty of data behind it.
86 ±8
Coding IQ 86.4, 95% interval 79–94. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.50cache read $0.05$1.50262K
38.5
Poor value (38.5). Costs more per task than its benchmark results predict. Plenty of data behind it.
40 ±9
Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Devstral Medium
🇫🇷
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/devstral-medium-latest@eu · latest · 🇪🇺 eu
 Eden AI
≈ 117
From 10 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.44$2.20262K
42.0
Poor value (42.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Devstral Medium
🇫🇷
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/devstral-medium-latest · latest
 Eden AI
≈ 117
From 10 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.40$2.00262K
42.0
Poor value (42.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Codestral 25.01
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
codestral-2508 · 2508
 Cortecs AI
116.6
From 10 benchmarks. A fair amount of data behind it.
Not enough data yet——256K
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. A fair amount of data behind it.
40 ±9
Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Codestral 25.01
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/codestral-2508 · 2508
 Eden AI
116.6
From 10 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30cache read $0.03$0.90256K
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. A fair amount of data behind it.
40 ±9
Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Codestral 25.01
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/codestral-2508@eu · 2508 · 🇪🇺 eu
 Eden AI
116.6
From 10 benchmarks. A fair amount of data behind it.
Not enough data yet$0.33cache read $0.033$0.99256K
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. A fair amount of data behind it.
40 ±9
Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Codestral 25.01
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/codestral-latest@eu · latest · 🇪🇺 eu
 Eden AI
116.6
From 10 benchmarks. A fair amount of data behind it.
Not enough data yet$0.33cache read $0.033$0.99256K
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. A fair amount of data behind it.
40 ±9
Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Codestral 25.01
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/codestral-latest · latest
 Eden AI
116.6
From 10 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30cache read $0.03$0.90256K
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. A fair amount of data behind it.
40 ±9
Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Codestral 25.01
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
codestral-2508 · 2508
 Llmgateway
116.6
From 10 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$0.90Not published by the provider
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. A fair amount of data behind it.
40 ±9
Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Codestral 25.01
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistralai/codestral-2508 · 2508
 OpenRouter
116.6
From 10 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30cache read $0.03$0.90256K
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. A fair amount of data behind it.
40 ±9
Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Codestral 25.01
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/codestral-latest · latest
 Requesty
116.6
From 10 benchmarks. A fair amount of data behind it.
Not enough data yet$0.33$0.99131K
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. A fair amount of data behind it.
40 ±9
Terse (40 ±9). Generates fewer 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 Medium 3
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Newer version
Newer versionMistral Medium 3.5We compared release dates and version names in our catalogue.
 Eden AI
116.4
From 50 benchmarks. A fair amount of data behind it.
Not enough data yet$0.44cache read $0.044$2.20262K
51.0
Fair value (51.0). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
132.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Medium 3
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Newer version
Newer versionMistral Medium 3.5We compared release dates and version names in our catalogue.
mistral/mistral-medium-3@eu · 🇪🇺 eu
 Eden AI
116.4
From 50 benchmarks. A fair amount of data behind it.
Not enough data yet$0.484cache read $0.0484$2.42262K
51.0
Fair value (51.0). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
132.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Medium 3
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Newer version
Newer versionMistral Medium 3.5We compared release dates and version names in our catalogue.
eu
 OpenRouter
116.4
From 50 benchmarks. A fair amount of data behind it.
Not enough data yet$0.44cache read $0.044$2.20131K
51.0
Fair value (51.0). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
132.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Ministral 14B
🇫🇷
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-14b-2512 · 2512
 Cortecs AI
115.6
From 33 benchmarks. A fair amount of data behind it.
Not enough data yet——256KNot enough data yetNot measuredNot measured
Ministral 14B
🇫🇷
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-14b-2512 · 2512
 Eden AI
115.6
From 33 benchmarks. A fair amount of data behind it.
Not enough data yet$0.20cache read $0.02$0.20262KNot enough data yetNot measuredNot measured
Ministral 14B
🇫🇷
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-14b-2512@eu · 2512 · 🇪🇺 eu
 Eden AI
115.6
From 33 benchmarks. A fair amount of data behind it.
Not enough data yet$0.22cache read $0.022$0.22262KNot enough data yetNot measuredNot measured
Ministral 14B
🇫🇷
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-14b-2512 · 2512
 Llmgateway
115.6
From 33 benchmarks. A fair amount of data behind it.
Not enough data yet$0.20$0.20Not published by the providerNot enough data yetNot measuredNot measured
Ministral 14B
🇫🇷
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-14b-2512 · eu+2512
 OpenRouter
115.6
From 33 benchmarks. A fair amount of data behind it.
Not enough data yet$0.22cache read $0.022$0.22262KNot enough data yetNot measuredNot measured
Ministral 14B
🇫🇷
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-14b-2512 · zdr+2512
 OpenRouter
115.6
From 33 benchmarks. A fair amount of data behind it.
Not enough data yet$0.20cache read $0.02$0.20262KNot enough data yetNot measuredNot measured
Mistral Medium 3.5
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
 Cortecs AI
115.3
From 173 benchmarks. Plenty of data behind it.
99 ±15
Coding IQ 98.6, 95% interval 84–114. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——256K
12.0
Poor value (12.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
141.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Medium 3.5
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
 Eden AI
115.3
From 173 benchmarks. Plenty of data behind it.
99 ±15
Coding IQ 98.6, 95% interval 84–114. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.50cache read $0.15$7.50262K
12.0
Poor value (12.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
141.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Medium 3.5
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/mistral-medium-3-5@eu · 🇪🇺 eu
 Eden AI
115.3
From 173 benchmarks. Plenty of data behind it.
99 ±15
Coding IQ 98.6, 95% interval 84–114. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.65cache read $0.165$8.25262K
12.0
Poor value (12.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
141.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Medium 3.5
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
 Llmgateway
115.3
From 173 benchmarks. Plenty of data behind it.
99 ±15
Coding IQ 98.6, 95% interval 84–114. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.50$7.50Not published by the provider
12.0
Poor value (12.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
141.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Medium 3.5
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistralai/mistral-medium-3-5:batch · batch
 OpenRouter
115.3
From 173 benchmarks. Plenty of data behind it.
99 ±15
Coding IQ 98.6, 95% interval 84–114. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.75$3.75262K
12.0
Poor value (12.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
141.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Medium 3.5
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
eu
 OpenRouter
115.3
From 173 benchmarks. Plenty of data behind it.
99 ±15
Coding IQ 98.6, 95% interval 84–114. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.65$8.25262K
12.0
Poor value (12.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
141.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Medium 3.5
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
zdr
 OpenRouter
115.3
From 173 benchmarks. Plenty of data behind it.
99 ±15
Coding IQ 98.6, 95% interval 84–114. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.50$7.50262K
12.0
Poor value (12.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
141.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Medium 3.5
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
 Requesty
115.3
From 173 benchmarks. Plenty of data behind it.
99 ±15
Coding IQ 98.6, 95% interval 84–114. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.65$8.25262K
12.0
Poor value (12.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
141.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Medium
🇫🇷
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-medium-2604 · 2604
 Eden AI
114.7
From 48 benchmarks. Plenty of data behind it.
≈ 91 ±14
Coding IQ 90.8, 95% interval 76–105. 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.
$1.50cache read $0.15$7.50262K
24.3
Poor value (24.3). Costs more per task than its benchmark results predict. A fair amount of data behind it.
59 ±9
Chatty (59 ±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 Medium
🇫🇷
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-medium-2604@eu · 2604 · 🇪🇺 eu
 Eden AI
114.7
From 48 benchmarks. Plenty of data behind it.
≈ 91 ±14
Coding IQ 90.8, 95% interval 76–105. 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.
$1.65cache read $0.165$8.25262K
24.3
Poor value (24.3). Costs more per task than its benchmark results predict. A fair amount of data behind it.
59 ±9
Chatty (59 ±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 Medium
🇫🇷
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-medium-latest@eu · latest · 🇪🇺 eu
 Eden AI
114.7
From 48 benchmarks. Plenty of data behind it.
≈ 91 ±14
Coding IQ 90.8, 95% interval 76–105. 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.
$1.65cache read $0.165$8.25262K
24.3
Poor value (24.3). Costs more per task than its benchmark results predict. A fair amount of data behind it.
59 ±9
Chatty (59 ±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 Medium
🇫🇷
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-medium-latest · latest
 Eden AI
114.7
From 48 benchmarks. Plenty of data behind it.
≈ 91 ±14
Coding IQ 90.8, 95% interval 76–105. 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.
$1.50cache read $0.15$7.50262K
24.3
Poor value (24.3). Costs more per task than its benchmark results predict. A fair amount of data behind it.
59 ±9
Chatty (59 ±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 Medium
🇫🇷
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-medium-latest · latest
 Requesty
114.7
From 48 benchmarks. Plenty of data behind it.
≈ 91 ±14
Coding IQ 90.8, 95% interval 76–105. 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.
$0.44$2.20131K
24.3
Poor value (24.3). Costs more per task than its benchmark results predict. A fair amount of data behind it.
59 ±9
Chatty (59 ±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
Devstral Small 2505
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral/devstral-small-latest · latest
 Requesty
112.7
From 14 benchmarks. A fair amount of data behind it.
≈ 83 ±10stale
Coding IQ 82.9, 95% interval 73–93. 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. Its newest result is over a year old.
$0.11$0.33131K
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Magistral Medium
🇫🇷
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/magistral-medium-latest@eu · latest · 🇪🇺 eu
 Eden AI
112.6
From 69 benchmarks. Plenty of data behind it.
92 ±10
Coding IQ 91.6, 95% interval 82–101. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.65cache read $0.165$8.25262K
22.3
Poor value (22.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
Magistral Medium
🇫🇷
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/magistral-medium-latest · latest
 Eden AI
112.6
From 69 benchmarks. Plenty of data behind it.
92 ±10
Coding IQ 91.6, 95% interval 82–101. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.50cache read $0.15$7.50262K
22.3
Poor value (22.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured

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

How this data works