Skip to content

Listings

All listings: Coreweave

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

Run by Coreweave

13 listings on this page where Coreweave 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
ModelProviderllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueEpoch Capabilities Index
Granite 4.2 8B
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.
ย Hugging Face
110.9
From 57 benchmarks. Plenty of data behind it.
90ย ยฑ17
Coding IQ 90.2, 95% interval 73โ€“108. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.06$0.15131KNot enough data yetNot measured
Granite 4.2 8B
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.
bf16 ยท ๐Ÿ‡บ๐Ÿ‡ธ US
ย NanoGPT
110.9
From 57 benchmarks. Plenty of data behind it.
90ย ยฑ17
Coding IQ 90.2, 95% interval 73โ€“108. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.063cache read $0.0158$0.1575Not published by the providerNot enough data yetNot measured
Granite 4.2 8B
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.
bf16
ย OpenRouter
110.9
From 57 benchmarks. Plenty of data behind it.
90ย ยฑ17
Coding IQ 90.2, 95% interval 73โ€“108. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.06cache read $0.015$0.15131KNot 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.
ย Hugging Face
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.
$0.71$0.71128K
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
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.
fp16 ยท ๐Ÿ‡บ๐Ÿ‡ธ US
ย NanoGPT
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.
$0.7455$0.7455Not published by the provider
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
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.
fp16
ย OpenRouter
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.
$0.71$0.71128K
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
Llama 3.1 8B 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-3.3-8B-InstructWe compared the version names in our catalogue.
ย Hugging Face
95.6
From 343 benchmarks. Plenty of data behind it.
70ย ยฑ9
Coding IQ 69.9, 95% interval 61โ€“79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.22$0.22131K
39.5
Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
Llama 3.1 8B 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-3.3-8B-InstructWe compared the version names in our catalogue.
bf16 ยท ๐Ÿ‡บ๐Ÿ‡ธ US
ย NanoGPT
95.6
From 343 benchmarks. Plenty of data behind it.
70ย ยฑ9
Coding IQ 69.9, 95% interval 61โ€“79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.231$0.231Not published by the provider
39.5
Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
Llama 3.1 8B 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-3.3-8B-InstructWe compared the version names in our catalogue.
bf16
ย OpenRouter
95.6
From 343 benchmarks. Plenty of data behind it.
70ย ยฑ9
Coding IQ 69.9, 95% interval 61โ€“79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.22$0.22131K
39.5
Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
Beam 1.0 501B A23B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
reflection/beam-1.0 ยท nvfp4 ยท ๐Ÿ‡บ๐Ÿ‡ธ US
ย NanoGPTNot enough data yetNot enough data yet$0.315cache read $0.042$1.05Not published by the providerNot enough data yetNot measured
Hermes High
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Router
This is a router, not a fixed model. The provider chooses which model answers, and that choice can change.
nvfp4 ยท ๐Ÿ‡บ๐Ÿ‡ธ US
ย NanoGPTNot enough data yetNot enough data yet$0.7875cache read $0.1995$3.15Not published by the providerNot enough data yetNot measured
Hermes Low
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Router
This is a router, not a fixed model. The provider chooses which model answers, and that choice can change.
nvfp4 ยท ๐Ÿ‡บ๐Ÿ‡ธ US
ย NanoGPTNot enough data yetNot enough data yet$0.7875cache read $0.1995$3.15Not published by the providerNot enough data yetNot measured
Hermes Medium
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Router
This is a router, not a fixed model. The provider chooses which model answers, and that choice can change.
nvfp4 ยท ๐Ÿ‡บ๐Ÿ‡ธ US
ย NanoGPTNot enough data yetNot enough data yet$0.7875cache read $0.1995$3.15Not published by the providerNot enough data yetNot measured

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

How this data works