Skip to content

Listings

All listings: Cortecs AI

Every listing for the models on page 4 of 5 of Cortecs AI, including each model's other versions and routes. Back to Cortecs AI

Sold by Cortecs AI

63 listings on this page sold by Cortecs 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
GLM 4.7 Flash
πŸ‡¨πŸ‡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.
Newer version
Newer versionGLM 5.3 FlashWe compared release dates and version names in our catalogue.
116.1
From 186 benchmarks. Plenty of data behind it.
83Β Β±10
Coding IQ 82.8, 95% interval 73–93. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
€0.072
β‰ˆ $0.079 USD (sorted by USD value)
€0.429
β‰ˆ $0.4708 USD (sorted by USD value)
203K
44.1
Poor value (44.1). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
GLM 4.7 Flash
πŸ‡¨πŸ‡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.
Newer version
Newer versionGLM 5.3 FlashWe compared release dates and version names in our catalogue.
Inference by Amazon Web Services
116.1
From 186 benchmarks. Plenty of data behind it.
83Β Β±10
Coding IQ 82.8, 95% interval 73–93. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”203K
44.1
Poor value (44.1). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Ministral 14B
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-14b-2512 Β· 2512
115.6
From 33 benchmarks. A fair amount of data behind it.
Not enough data yet
€0.215
β‰ˆ $0.2359 USD (sorted by USD value)
€0.215
β‰ˆ $0.2359 USD (sorted by USD value)
256KNot enough data yetNot measuredNot measured
Ministral 14B
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-14b-2512 Β· 2512
Inference by Amazon Web Services
115.6
From 33 benchmarks. A fair amount of data behind it.
Not enough data yetβ€”β€”256KNot enough data yetNot measuredNot measured
Ministral 14B
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-14b-2512 Β· 2512
Inference by Mistral AI
115.6
From 33 benchmarks. A fair amount of data behind it.
Not enough data yetβ€”β€”256KNot enough data yetNot measuredNot measured
Qwen3 32B
πŸ‡¨πŸ‡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.
115.6
From 234 benchmarks. Plenty of data behind it.
85Β Β±9
Coding IQ 84.8, 95% interval 76–93. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
€0.161
β‰ˆ $0.1767 USD (sorted by USD value)
€0.626
β‰ˆ $0.687 USD (sorted by USD value)
16K
35.8
Poor value (35.8). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
136.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3 32B
πŸ‡¨πŸ‡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.
Inference by Amazon Web Services
115.6
From 234 benchmarks. Plenty of data behind it.
85Β Β±9
Coding IQ 84.8, 95% interval 76–93. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”16K
35.8
Poor value (35.8). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
136.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4.1 mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.4 miniWe compared the version names in our catalogue.
115.4
From 375 benchmarks. Plenty of data behind it.
91Β Β±8
Coding IQ 91.3, 95% interval 84–99. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
€0.408cache read €0.102
β‰ˆ $0.4477 USD (sorted by USD value)
€1.633
β‰ˆ $1.792 USD (sorted by USD value)
1M
46.2
Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
134.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4.1 mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.4 miniWe compared the version names in our catalogue.
Inference by Microsoft Azure
115.4
From 375 benchmarks. Plenty of data behind it.
91Β Β±8
Coding IQ 91.3, 95% interval 84–99. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”1M
46.2
Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
134.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5 nano
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared release dates and version names in our catalogue.
115.3
From 332 benchmarks. Plenty of data behind it.
93Β Β±13
Coding IQ 92.7, 95% interval 80–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
€0.056cache read €0.009
β‰ˆ $0.0615 USD (sorted by USD value)
€0.408
β‰ˆ $0.4477 USD (sorted by USD value)
400K
46.3
Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 Β±9
Typical (51 Β±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.
139.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5 nano
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared release dates and version names in our catalogue.
Inference by Microsoft Azure
115.3
From 332 benchmarks. Plenty of data behind it.
93Β Β±13
Coding IQ 92.7, 95% interval 80–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”400K
46.3
Poor value (46.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 Β±9
Typical (51 Β±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.
139.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Medium 3.5
πŸ‡«πŸ‡·
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.
99Β Β±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.
€1.375cache read €0.138
β‰ˆ $1.5089 USD (sorted by USD value)
€7.04
β‰ˆ $7.7256 USD (sorted by USD value)
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
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Inference by Mistral AI
115.3
From 173 benchmarks. Plenty of data behind it.
99Β Β±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.
β€”β€”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
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Inference by Scaleway
115.3
From 173 benchmarks. Plenty of data behind it.
99Β Β±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.
β€”β€”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
Qwen3 30B A3B Instruct
πŸ‡¨πŸ‡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.
qwen3-30b-a3b-instruct-2507
114.9
From 100 benchmarks. Plenty of data behind it.
β‰ˆ 86Β Β±20
Coding IQ 86.4, 95% interval 67–106. 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.
€0.089
β‰ˆ $0.0977 USD (sorted by USD value)
€0.268
β‰ˆ $0.2941 USD (sorted by USD value)
262K
36.5
Poor value (36.5). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
134.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3 30B A3B Instruct
πŸ‡¨πŸ‡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.
qwen3-30b-a3b-instruct-2507
Inference by Nebius AI Studio
114.9
From 100 benchmarks. Plenty of data behind it.
β‰ˆ 86Β Β±20
Coding IQ 86.4, 95% interval 67–106. 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.
β€”β€”262K
36.5
Poor value (36.5). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
134.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Pixtral Large
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
pixtral-large-2502 Β· 2502
114.2
From 15 benchmarks. Plenty of data behind it.
Not enough data yet
€1.789
β‰ˆ $1.9632 USD (sorted by USD value)
€5.366
β‰ˆ $5.8886 USD (sorted by USD value)
128K
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
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
pixtral-large-2502 Β· 2502
Inference by Amazon Web Services
114.2
From 15 benchmarks. Plenty of data behind it.
Not enough data yetβ€”β€”128K
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
GPT 4o
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
113.7
From 761 benchmarks. Plenty of data behind it.
77Β Β±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
€2.553cache read €1.276
β‰ˆ $2.8016 USD (sorted by USD value)
€10.208
β‰ˆ $11.2021 USD (sorted by USD value)
128K
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 4o
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Inference by Microsoft Azure
113.7
From 761 benchmarks. Plenty of data behind it.
77Β Β±10
Coding IQ 77.4, 95% interval 67–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”128K
24.6
Poor value (24.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
128.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Small 3.2 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-3.2-24b-instruct-2506 Β· 2506
113.3
From 50 benchmarks. Plenty of data behind it.
Not enough data yet
€0.09
β‰ˆ $0.0988 USD (sorted by USD value)
€0.28
β‰ˆ $0.3073 USD (sorted by USD value)
131K
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 Small 3.2 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-3.2-24b-instruct-2506 Β· 2506
Inference by Berget AI
113.3
From 50 benchmarks. Plenty of data behind it.
Not enough data yetβ€”β€”131K
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 Small 3.2 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-3.2-24b-instruct-2506 Β· 2506
Inference by OVHcloud
113.3
From 50 benchmarks. Plenty of data behind it.
Not enough data yetβ€”β€”131K
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 Small 3.2 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-3.2-24b-instruct-2506 Β· 2506
Inference by Scaleway
113.3
From 50 benchmarks. Plenty of data behind it.
Not enough data yetβ€”β€”131K
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
Qwen3.5 9B
πŸ‡¨πŸ‡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.
113.2
From 223 benchmarks. Plenty of data behind it.
86Β Β±8
Coding IQ 85.6, 95% interval 77–94. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
€0.10
β‰ˆ $0.1097 USD (sorted by USD value)
€0.15
β‰ˆ $0.1646 USD (sorted by USD value)
262K
55.4
Good value (55.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
139.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3.5 9B
πŸ‡¨πŸ‡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.
Inference by Ionos
113.2
From 223 benchmarks. Plenty of data behind it.
86Β Β±8
Coding IQ 85.6, 95% interval 77–94. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”262K
55.4
Good value (55.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
139.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3.5 9B
πŸ‡¨πŸ‡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.
Inference by OVHcloud
113.2
From 223 benchmarks. Plenty of data behind it.
86Β Β±8
Coding IQ 85.6, 95% interval 77–94. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”262K
55.4
Good value (55.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
139.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Nova 2 Lite
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
112.6
From 78 benchmarks. Plenty of data behind it.
94Β Β±41
Coding IQ 94.4, 95% interval 53–136. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
€0.335
β‰ˆ $0.3676 USD (sorted by USD value)
€2.822
β‰ˆ $3.0968 USD (sorted by USD value)
1M
38.2
Poor value (38.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Nova 2 Lite
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Inference by Amazon Web Services
112.6
From 78 benchmarks. Plenty of data behind it.
94Β Β±41
Coding IQ 94.4, 95% interval 53–136. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”1M
38.2
Poor value (38.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
GPT OSS 20b
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, 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.
111.3
From 251 benchmarks. Plenty of data behind it.
88Β Β±12
Coding IQ 88.2, 95% interval 76–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
€0.04
β‰ˆ $0.0439 USD (sorted by USD value)
€0.15
β‰ˆ $0.1646 USD (sorted by USD value)
131K
48.9
Fair value (48.9). Costs per task about what its benchmark results predict. Plenty of data behind it.
40 Β±9
Terse (40 Β±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.
134.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT OSS 20b
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, 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.
Inference by Amazon Web Services
111.3
From 251 benchmarks. Plenty of data behind it.
88Β Β±12
Coding IQ 88.2, 95% interval 76–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”131K
48.9
Fair value (48.9). Costs per task about what its benchmark results predict. Plenty of data behind it.
40 Β±9
Terse (40 Β±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.
134.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT OSS 20b
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, 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.
Inference by OVHcloud
111.3
From 251 benchmarks. Plenty of data behind it.
88Β Β±12
Coding IQ 88.2, 95% interval 76–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”131K
48.9
Fair value (48.9). Costs per task about what its benchmark results predict. Plenty of data behind it.
40 Β±9
Terse (40 Β±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.
134.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Nemotron 3 Nano 30B A3B
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, 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.
nvidia-nemotron-3-nano-30b-a3b
109.7
From 137 benchmarks. Plenty of data behind it.
91Β Β±14
Coding IQ 91.4, 95% interval 77–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
€0.054
β‰ˆ $0.0593 USD (sorted by USD value)
€0.215
β‰ˆ $0.2359 USD (sorted by USD value)
256K
36.7
Poor value (36.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Nemotron 3 Nano 30B A3B
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, 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.
nvidia-nemotron-3-nano-30b-a3b
Inference by Amazon Web Services
109.7
From 137 benchmarks. Plenty of data behind it.
91Β Β±14
Coding IQ 91.4, 95% interval 77–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”256K
36.7
Poor value (36.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Nemotron 3 Nano 30B A3B
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, 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.
nvidia-nemotron-3-nano-30b-a3b
Inference by Nebius AI Studio
109.7
From 137 benchmarks. Plenty of data behind it.
91Β Β±14
Coding IQ 91.4, 95% interval 77–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”256K
36.7
Poor value (36.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen2.5 VL 72B Instruct
πŸ‡¨πŸ‡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.
108.8
From 97 benchmarks. Plenty of data behind it.
Not enough data yet
€0.91
β‰ˆ $0.9986 USD (sorted by USD value)
€0.91
β‰ˆ $0.9986 USD (sorted by USD value)
32K
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen2.5 VL 72B Instruct
πŸ‡¨πŸ‡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.
Inference by OVHcloud
108.8
From 97 benchmarks. Plenty of data behind it.
Not enough data yetβ€”β€”32K
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
GPT-4o mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
108.6
From 478 benchmarks. Plenty of data behind it.
72Β Β±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
€0.153cache read €0.077
β‰ˆ $0.1679 USD (sorted by USD value)
€0.613
β‰ˆ $0.6727 USD (sorted by USD value)
128K
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4o mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Inference by Microsoft Azure
108.6
From 478 benchmarks. Plenty of data behind it.
72Β Β±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”128K
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemma 3 27B IT
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, 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.
108.5
From 365 benchmarks. Plenty of data behind it.
73Β Β±8
Coding IQ 72.7, 95% interval 65–81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
€0.089
β‰ˆ $0.0977 USD (sorted by USD value)
€0.268
β‰ˆ $0.2941 USD (sorted by USD value)
131K
46.2
Poor value (46.2). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
127.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemma 3 27B IT
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, 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.
Inference by Nebius AI Studio
108.5
From 365 benchmarks. Plenty of data behind it.
73Β Β±8
Coding IQ 72.7, 95% interval 65–81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”131K
46.2
Poor value (46.2). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
127.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Llama 3.3 70B Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, 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.
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±9
Coding IQ 77.1, 95% interval 68–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
€0.65
β‰ˆ $0.7133 USD (sorted by USD value)
€0.65
β‰ˆ $0.7133 USD (sorted by USD value)
131K
31.6
Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
126.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Llama 3.3 70B Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, 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.
Inference by Ionos
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±9
Coding IQ 77.1, 95% interval 68–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”131K
31.6
Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
126.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Llama 3.3 70B Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, 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.
Inference by OVHcloud
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±9
Coding IQ 77.1, 95% interval 68–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”131K
31.6
Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
126.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Llama 3.3 70B Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, 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.
Inference by Scaleway
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±9
Coding IQ 77.1, 95% interval 68–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”131K
31.6
Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
126.2
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-2402 Β· 2402
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.
€3.846
β‰ˆ $4.2205 USD (sorted by USD value)
€11.627
β‰ˆ $12.7593 USD (sorted by USD value)
32K
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-2402 Β· 2402
Inference by Amazon Web Services
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.
β€”β€”32K
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-2503 Β· 2503
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
β‰ˆ $0.1097 USD (sorted by USD value)
€0.30
β‰ˆ $0.3292 USD (sorted by USD value)
128K
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.
€0.14cache read €0.014
β‰ˆ $0.1536 USD (sorted by USD value)
€0.561
β‰ˆ $0.6156 USD (sorted by USD value)
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-small-2603 Β· 2603
Inference by Aki
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-small-2503 Β· 2503
Inference by Ionos
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€”128K
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
Inference by Mistral 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
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
€0.161
β‰ˆ $0.1767 USD (sorted by USD value)
€0.161
β‰ˆ $0.1767 USD (sorted by USD value)
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.
ministral-8b-2512 Β· 2512
Inference by Amazon Web Services
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.
ministral-8b-2512 Β· 2512
Inference by Mistral 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
Nova Pro
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
nova-pro-v1
106.4
From 119 benchmarks. Plenty of data behind it.
Not enough data yet
€0.824
β‰ˆ $0.9042 USD (sorted by USD value)
€3.295
β‰ˆ $3.6159 USD (sorted by USD value)
300K
36.8
Poor value (36.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Nova Pro
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
nova-pro-v1
Inference by Amazon Web Services
106.4
From 119 benchmarks. Plenty of data behind it.
Not enough data yetβ€”β€”300K
36.8
Poor value (36.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
GPT-4.1 nano
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared the version names in our catalogue.
105.3
From 325 benchmarks. Plenty of data behind it.
75Β Β±9
Coding IQ 74.7, 95% interval 66–83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
€0.102cache read €0.028
β‰ˆ $0.1119 USD (sorted by USD value)
€0.408
β‰ˆ $0.4477 USD (sorted by USD value)
1M
27.8
Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
126.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4.1 nano
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 5.4 NanoWe compared the version names in our catalogue.
Inference by Microsoft Azure
105.3
From 325 benchmarks. Plenty of data behind it.
75Β Β±9
Coding IQ 74.7, 95% interval 66–83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”1M
27.8
Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
126.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Nova Lite
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
nova-lite-v1
104.7
From 107 benchmarks. Plenty of data behind it.
β‰ˆ 82Β Β±10
Coding IQ 82.3, 95% interval 72–93. 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.
€0.062
β‰ˆ $0.068 USD (sorted by USD value)
€0.247
β‰ˆ $0.2711 USD (sorted by USD value)
300K
41.5
Poor value (41.5). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
38 Β±9
Terse (38 Β±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
Nova Lite
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
nova-lite-v1
Inference by Amazon Web Services
104.7
From 107 benchmarks. Plenty of data behind it.
β‰ˆ 82Β Β±10
Coding IQ 82.3, 95% interval 72–93. 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.
β€”β€”300K
41.5
Poor value (41.5). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
38 Β±9
Terse (38 Β±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
Nova Micro
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
nova-micro-v1
103.3
From 102 benchmarks. Plenty of data behind it.
Not enough data yet
€0.036
β‰ˆ $0.0395 USD (sorted by USD value)
€0.143
β‰ˆ $0.1569 USD (sorted by USD value)
128K
47.4
Poor value (47.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Nova Micro
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
nova-micro-v1
Inference by Amazon Web Services
103.3
From 102 benchmarks. Plenty of data behind it.
Not enough data yetβ€”β€”128K
47.4
Poor value (47.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured

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

How this data works