Skip to content

Listings

All listings: Empiriolabs

Every listing for the models on page 3 of 9 of Empiriolabs, including each model's other versions and routes. Back to Empiriolabs

Sold by Empiriolabs

25 listings on this page sold by Empiriolabs.

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
Qwen3.6 35B A3B
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.
eschamoe W2: 2-bit weights + INT8 dense + FP16 KV
119.8
From 160 benchmarks. Plenty of data behind it.
95Β Β±14
Coding IQ 94.8, 95% interval 81–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.07cache read $0.035$0.42131K
38.5
Poor value (38.5). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
144.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
118.6
From 76 benchmarks. Plenty of data behind it.
Not enough data yet$0.12>128k $0.24$0.50>128k $1.00229K
45.0
Poor value (45.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen3.5 Omni Flash
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
117.3
From 54 benchmarks. A fair amount of data behind it.
Not enough data yet$0.80$4.40197KNot enough data yetNot 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.
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.
$0.00$0.00203K
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
Gemini 2.5 Pro TTS
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
β‰ˆ 115
From 16 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$3.00$60.00Not published by the providerNot enough data yetNot measuredNot measured
β‰ˆ 114
From 38 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured
Mistral Small 3.1
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
β‰ˆ 113
From 3 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yetβ€”β€”90KNot enough data yetNot 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.
FP8 weights + FP8 KV
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.
$0.09cache read $0.045$0.13262K
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.
nova-lite-2
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.
$0.38cache read $0.2128$3.161M
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
Wan 2.7
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionWan 3.0We compared release dates and version names in our catalogue.
β‰ˆ 112
From 4 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured
Nova Pro 1.0
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
β‰ˆ 111
From 64 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$2.40$9.60317KNot enough data yetNot measuredNot measured
Qwen Image 2.1
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
β‰ˆ 109
From 34 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured
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.
gemma-3-27b
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
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-4
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15$0.60262K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Nova Lite 1.0
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionNova 2 LiteWe compared release dates and version names in our catalogue.
107.4
From 65 benchmarks. A fair amount of data behind it.
Not enough data yet$0.069cache read $0.0386$0.28317K
45.7
Poor value (45.7). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen3.5 4B
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.
FP8 weights + FP8 KV
107.0
From 129 benchmarks. Plenty of data behind it.
β‰ˆ 78Β Β±12
Coding IQ 77.8, 95% interval 66–90. 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.
$0.04cache read $0.02$0.07262KNot enough data yetNot measuredNot measured
Nova Micro 1.0
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
104.5
From 62 benchmarks. A fair amount of data behind it.
Not enough data yet$0.04cache read $0.0224$0.16133K
44.2
Poor value (44.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
HunyuanVideo 1.5
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Mixed FP16/FP8
β‰ˆ 104
From 7 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured
Doubao Seedream 4.5
Newer version
Newer versionSeedream 5.5We compared the version names in our catalogue.
seedream-4-5
98.2
From 177 benchmarks. A fair amount of data behind it.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured
Doubao Seedream 4-0
Newer version
Newer versionSeedream 5.5We compared release dates and version names in our catalogue.
seedream-4-0
93.4
From 182 benchmarks. A fair amount of data behind it.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured
FLUX.2 [klein] 4B
πŸ‡©πŸ‡ͺ
Maker headquartered in DE, according to the company's own website. The citation is on the model page.
BF16
89.9
From 161 benchmarks. A fair amount of data behind it.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured
Hunyuan Image V3
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
hunyuan-image-3
89.2
From 42 benchmarks. A fair amount of data behind it.
Not enough data yetβ€”β€”Not published by the providerNot enough data yetNot measuredNot measured
Aplomb 1BF16 weights
Doesn’t apply to this modelDoesn’t apply to this model$0.02Doesn’t apply to this model1MDoesn’t apply to this modelDoesn’t apply to this modelDoesn’t apply to this model
qwen3-7-flash:variant1
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.028cache read $0.006$0.11984KNot enough data yetNot measuredNot measured
qwen3-5-flash:variant1
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Not enough data yetNot enough data yet$0.029>128k $0.115$0.287>128k $1.147996KNot enough data yetNot measuredNot measured

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

How this data works