Skip to content

Listings

All listings: Aihubmix

Every listing for the models on page 11 of 20 of Aihubmix, including each model's other versions and routes. Back to Aihubmix

Sold by Aihubmix

29 listings on this page sold by Aihubmix.

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
Modelllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueEpoch Capabilities Index
GPT-4o mini
๐Ÿ‡บ๐Ÿ‡ธ
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.
72ย ยฑ18
Coding IQ 71.8, 95% interval 54โ€“90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.075$0.60128K
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4o mini
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gpt-4o-mini-2024-07-18 ยท 2024-07-18
108.6
From 478 benchmarks. Plenty of data behind it.
72ย ยฑ18
Coding IQ 71.8, 95% interval 54โ€“90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.075$0.60Not published by the provider
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemma 3 27B IT
๐Ÿ‡บ๐Ÿ‡ธ
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.
73ย ยฑ8
Coding IQ 72.7, 95% interval 65โ€“81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20$0.20Not published by the provider
46.2
Poor value (46.2). Costs more per task than its benchmark results predict. A fair amount of data behind it.
127.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Llama 3 70B Instruct
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionLlama 3.3 70B InstructWe compared release dates and version names in our catalogue.
aihubmix-Llama-3-70B-Instruct
108.2
From 199 benchmarks. Plenty of data behind it.
โ‰ˆ 77ย ยฑ11
Coding IQ 76.5, 95% interval 66โ€“87. 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.
$0.70$0.70Not published by the provider
49.9
Fair value (49.9). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
DeepSeek V2 Chat
๐Ÿ‡จ๐Ÿ‡ณ
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionDeepSeek V3.1We compared release dates and version names in our catalogue.
108.1
From 48 benchmarks. A fair amount of data behind it.
Not enough data yet$0.16$0.32Not published by the providerNot enough data yetNot measured
Llama 3.3 70B Instruct
๐Ÿ‡บ๐Ÿ‡ธ
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.
77ย ยฑ9
Coding IQ 77.1, 95% interval 68โ€“86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.60$1.20131K
31.6
Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it.
126.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
๐Ÿ‡ซ๐Ÿ‡ท
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
aihubmix-Mistral-large
108.0
From 293 benchmarks. Plenty of data behind it.
72ย ยฑ9
Coding IQ 72.2, 95% interval 63โ€“81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00$12.00Not published by the provider
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
๐Ÿ‡ซ๐Ÿ‡ท
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Mistral-large-2407 ยท 2407
108.0
From 293 benchmarks. Plenty of data behind it.
72ย ยฑ9
Coding IQ 72.2, 95% interval 63โ€“81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$9.00Not published by the provider
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
๐Ÿ‡ซ๐Ÿ‡ท
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
aihubmix-Mistral-Large-2411 ยท 2411
108.0
From 293 benchmarks. Plenty of data behind it.
72ย ยฑ9
Coding IQ 72.2, 95% interval 63โ€“81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00$6.00Not published by the provider
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemma 3 12B IT
๐Ÿ‡บ๐Ÿ‡ธ
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.
Newer version
Newer versionGemma 4 12B ItWe compared release dates and version names in our catalogue.
107.6
From 331 benchmarks. Plenty of data behind it.
68ย ยฑ19
Coding IQ 68.1, 95% interval 49โ€“87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20$0.20Not published by the provider
41.7
Poor value (41.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
Qwen2 72B Instruct
๐Ÿ‡จ๐Ÿ‡ณ
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen2.5 72B InstructWe compared release dates and version names in our catalogue.
107.3
From 265 benchmarks. Plenty of data behind it.
โ‰ˆ 76ย ยฑ11
Coding IQ 76.2, 95% interval 65โ€“87. 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.
$0.80$0.80Not published by the provider
34.3
Poor value (34.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
DeepSeek R1 Distill Qwen 32B
๐Ÿ‡จ๐Ÿ‡ณ
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
107.1
From 40 benchmarks. Plenty of data behind it.
โ‰ˆ 81ย ยฑ12stale
Coding IQ 80.5, 95% interval 68โ€“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.
$0.20$0.20Not published by the providerNot enough data yetNot measured
DeepSeek R1 Distill Qwen 14B
๐Ÿ‡จ๐Ÿ‡ณ
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
107.0
From 24 benchmarks. Plenty of data behind it.
Not enough data yet$0.10$0.10Not published by the providerNot enough data yetNot measured
Llama 3.1 70B Instruct
๐Ÿ‡บ๐Ÿ‡ธ
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.
Newer version
Newer versionLlama 3.3 70B InstructWe compared release dates and version names in our catalogue.
aihubmix-Llama-3-1-70B-Instruct
106.8
From 168 benchmarks. Plenty of data behind it.
โ‰ˆ 80ย ยฑ11
Coding IQ 80.3, 95% interval 69โ€“91. 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.
$0.60$0.78Not published by the provider
41.0
Poor value (41.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Llama 3.1 70B Instruct
๐Ÿ‡บ๐Ÿ‡ธ
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.
Newer version
Newer versionLlama 3.3 70B InstructWe compared release dates and version names in our catalogue.
meta-llama/llama-3.1-70b-instruct:free ยท free
106.8
From 168 benchmarks. Plenty of data behind it.
โ‰ˆ 80ย ยฑ11
Coding IQ 80.3, 95% interval 69โ€“91. 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.
$0.02$0.02Not published by the provider
41.0
Poor value (41.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
QVQ 72B Preview
๐Ÿ‡จ๐Ÿ‡ณ
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
106.7
From 14 benchmarks. A fair amount of data behind it.
Not enough data yet$1.20$1.20Not published by the providerNot enough data yetNot measured
GPT 4 1106 Preview
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.5-previewWe compared the version names in our catalogue.
โ‰ˆ 107
From 72 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$10.00$30.00Not published by the providerNot enough data yetNot measured
Llama 4 Scout
๐Ÿ‡บ๐Ÿ‡ธ
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.
106.3
From 347 benchmarks. Plenty of data behind it.
69ย ยฑ8
Coding IQ 69.3, 95% interval 61โ€“78. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20$0.20131K
30.3
Poor value (30.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
127.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen 2.5 Coder 32B Instruct
๐Ÿ‡จ๐Ÿ‡ณ
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.
106.3
From 104 benchmarks. Plenty of data behind it.
81ย ยฑ9
Coding IQ 80.7, 95% interval 72โ€“89. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.16$0.16Not published by the provider
50.7
Fair value (50.7). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Llama 3.2 90B Vision Instruct
๐Ÿ‡บ๐Ÿ‡ธ
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.
106.1
From 54 benchmarks. Plenty of data behind it.
Not enough data yet$0.50$0.50Not published by the provider
57.0
Good value (57.0). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Meta Llama 3 70b
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionLlama 3.1 70BWe compared release dates and version names in our catalogue.
106.1
From 92 benchmarks. Plenty of data behind it.
Not enough data yet$4.795$4.795Not published by the provider
39.8
Poor value (39.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
121.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Phi 4
๐Ÿ‡บ๐Ÿ‡ธ
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.
aihub-Phi-4
105.9
From 144 benchmarks. Plenty of data behind it.
โ‰ˆ 78ย ยฑ11
Coding IQ 77.6, 95% interval 66โ€“89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.12$0.4816K
51.2
Fair value (51.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
129.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3 4B
๐Ÿ‡จ๐Ÿ‡ณ
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen3.5 4BWe compared release dates and version names in our catalogue.
105.8
From 116 benchmarks. Plenty of data behind it.
โ‰ˆ 78ย ยฑ9
Coding IQ 78.4, 95% interval 69โ€“88. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.046$0.46Not published by the provider
32.9
Poor value (32.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
Jamba 1.5 Large
๐Ÿ‡ฎ๐Ÿ‡ฑ
Maker headquartered in IL, according to the company's own website. The citation is on the model page.
aihubmix-Jamba-1-5-Large
105.4
From 113 benchmarks. Plenty of data behind it.
Not enough data yet$2.20$8.80Not published by the provider
27.7
Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
GPT-4.1 nano
๐Ÿ‡บ๐Ÿ‡ธ
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.
75ย ยฑ9
Coding IQ 74.7, 95% interval 66โ€“83. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10cache read $0.025$0.401M
27.8
Poor value (27.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
126.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30cache read $0.03$2.49966K
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
GLM 4 Vision
๐Ÿ‡จ๐Ÿ‡ณ
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
glm-4v
104.9
From 19 benchmarks. Plenty of data behind it.
Not enough data yet$14.20$14.20Not published by the providerNot enough data yetNot measured
DeepSeek VL2
๐Ÿ‡จ๐Ÿ‡ณ
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
104.8
From 23 benchmarks. Plenty of data behind it.
Not enough data yet$0.16$0.16Not published by the providerNot enough data yetNot measured
Qwen 2.5 14B Instruct
๐Ÿ‡จ๐Ÿ‡ณ
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
104.8
From 147 benchmarks. Plenty of data behind it.
76ย ยฑ10stale
Coding IQ 75.7, 95% interval 65โ€“86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old.
$0.40$1.20Not published by the providerNot enough data yetNot measured

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

How this data works