Skip to content

Listings

All listings: Amazon Web Services

Every listing for the models on page 4 of 9 of Amazon Web Services, including each model's other versions and routes. Back to Amazon Web Services

Sold by Amazon Web Services

53 listings on this page sold by Amazon Web Services.

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
Claude Haiku 3.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared the version names in our catalogue.
regional.anthropic.claude-3-5-haiku-20241022-v1:0 · 20241022 · regional
110.1
From 238 benchmarks. Plenty of data behind it.
79 ±8
Coding IQ 79.4, 95% interval 72–87. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.80cache read $0.08$4.00cache write $1.00Not published by the provider
19.4
Poor value (19.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
124.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 3.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared the version names in our catalogue.
claude-3-5-haiku
110.1
From 238 benchmarks. Plenty of data behind it.
79 ±8
Coding IQ 79.4, 95% interval 72–87. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.80$4.00Not published by the provider
19.4
Poor value (19.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
124.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 3.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared the version names in our catalogue.
eu.anthropic.claude-3-5-haiku-20241022-v1:0 · 20241022 · 🇪🇺 eu
110.1
From 238 benchmarks. Plenty of data behind it.
79 ±8
Coding IQ 79.4, 95% interval 72–87. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.80cache read $0.08$4.00cache write $1.00200K
19.4
Poor value (19.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
124.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 3.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared the version names in our catalogue.
bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0 · 20241022 · 🇺🇸 us
110.1
From 238 benchmarks. Plenty of data behind it.
79 ±8
Coding IQ 79.4, 95% interval 72–87. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.80cache read $0.08$4.00cache write $1.00200K
19.4
Poor value (19.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
124.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 3.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared the version names in our catalogue.
anthropic.claude-3-5-haiku-20241022-v1:0 · 20241022
110.1
From 238 benchmarks. Plenty of data behind it.
79 ±8
Coding IQ 79.4, 95% interval 72–87. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.80cache read $0.08$4.00cache write $1.00200K
19.4
Poor value (19.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
124.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 3.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared the version names in our catalogue.
claude-3-5-haiku-20241022 · 20241022
110.1
From 238 benchmarks. Plenty of data behind it.
79 ±8
Coding IQ 79.4, 95% interval 72–87. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.80$4.00Not published by the provider
19.4
Poor value (19.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
124.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
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.
mistral.magistral-small-2509 · 2509
109.2
From 42 benchmarks. Plenty of data behind it.
Not enough data yet$0.50batch $0.25$1.50batch $0.75128K
27.6
Poor value (27.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
Gemma 3 27B IT
🇺🇸
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.
google.gemma-3-27b-it
108.5
From 365 benchmarks. Plenty of data behind it.
73 ±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.
$0.23batch $0.12$0.38batch $0.19128K
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
🇺🇸
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.
us.meta.llama3-3-70b-instruct-v1:0 · 🇺🇸 us
108.1
From 278 benchmarks. Plenty of data behind it.
77 ±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.
$0.72batch $0.36$0.72batch $0.36128K
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
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral.mistral-large-2402-v1:0 · 2402
108.0
From 293 benchmarks. Plenty of data behind it.
72 ±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.
$4.00$12.0032K
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
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral.mistral-large-2407-v1:0 · 2407
108.0
From 293 benchmarks. Plenty of data behind it.
72 ±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.
$2.00$6.00128K
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
Gemma 3 12B IT
🇺🇸
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.
google.gemma-3-12b-it
107.6
From 331 benchmarks. Plenty of data behind it.
68 ±19
Coding IQ 68.1, 95% interval 49–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.09batch $0.05$0.29batch $0.15128K
41.7
Poor value (41.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Llama 3.1 70B Instruct
🇺🇸
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.
us.meta.llama3-1-70b-instruct-v1:0 · 🇺🇸 us
106.8
From 168 benchmarks. Plenty of data behind it.
≈ 80 ±11
Coding IQ 80.3, 95% interval 69–91. 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.
$0.72batch $0.36$0.72batch $0.36128K
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 measuredNot measured
Ministral 3 3b 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.
mistral.ministral-3-3b-instruct
106.4
From 8 benchmarks. A fair amount of data behind it.
Not enough data yet$0.10batch $0.05$0.10batch $0.05128KNot enough data yetNot measuredNot measured
Nova Pro
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.nova-pro-v1:0
106.4
From 119 benchmarks. Plenty of data behind it.
Not enough data yet$0.80cache read $0.20batch $0.40$3.20batch $1.60300K
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.nova-pro-v1:0:24k · 24k
106.4
From 119 benchmarks. Plenty of data behind it.
Not enough data yet——Not published by the provider
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.nova-pro-v1:0:300k · 300k
106.4
From 119 benchmarks. Plenty of data behind it.
Not enough data yet——Not published by the provider
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
eu.amazon.nova-pro-v1%3A0 · 🇪🇺 eu
106.4
From 119 benchmarks. Plenty of data behind it.
Not enough data yet$0.80cache read $0.2175$3.20cache write $0.92300K
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.amazon.nova-pro-v1%3A0 · 🇺🇸 us
106.4
From 119 benchmarks. Plenty of data behind it.
Not enough data yet$0.80cache read $0.20batch $0.40$3.20batch $1.60300K
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
bedrock/ap-southeast-4/apac.amazon.nova-pro-v1:0 · apac
106.4
From 119 benchmarks. Plenty of data behind it.
Not enough data yet$0.87cache read $0.2175$3.48300K
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon-nova/nova-pro-v1
106.4
From 119 benchmarks. Plenty of data behind it.
Not enough data yet$0.80$3.20300K
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.amazon.nova-pro-v1 · 🇺🇸 us
106.4
From 119 benchmarks. Plenty of data behind it.
Not enough data yet$0.80$3.20Not published by the provider
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
Llama 4 Scout
🇺🇸
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.
us.meta.llama4-scout-17b-instruct-v1:0 · 🇺🇸 us
106.2
From 347 benchmarks. Plenty of data behind it.
69 ±8
Coding IQ 69.3, 95% interval 61–78. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.17batch $0.085$0.66batch $0.3310M
30.3
Poor value (30.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
127.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemma 4 E2B IT
🇺🇸
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.
bedrock_mantle/google.gemma-4-e2b
≈ 106
From 9 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.04batch $0.02$0.08batch $0.04128KNot enough data yetNot measuredNot measured
Nova Lite
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.nova-lite-v1:0
104.7
From 107 benchmarks. Plenty of data behind it.
≈ 82 ±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.
$0.06cache read $0.015batch $0.03$0.24batch $0.12300K
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 ±9
Terse (38 ±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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.nova-lite-v1:0:24k · 24k
104.7
From 107 benchmarks. Plenty of data behind it.
≈ 82 ±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.
——Not published by the provider
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 ±9
Terse (38 ±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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.nova-lite-v1:0:300k · 300k
104.7
From 107 benchmarks. Plenty of data behind it.
≈ 82 ±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.
——Not published by the provider
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 ±9
Terse (38 ±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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
eu.amazon.nova-lite-v1%3A0 · 🇪🇺 eu
104.7
From 107 benchmarks. Plenty of data behind it.
≈ 82 ±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.
$0.06cache read $0.0163$0.24cache write $0.069300K
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 ±9
Terse (38 ±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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.amazon.nova-lite-v1%3A0 · 🇺🇸 us
104.7
From 107 benchmarks. Plenty of data behind it.
≈ 82 ±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.
$0.06cache read $0.015batch $0.03$0.24batch $0.12300K
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 ±9
Terse (38 ±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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
bedrock/il-central-1/apac.amazon.nova-lite-v1:0 · apac
104.7
From 107 benchmarks. Plenty of data behind it.
≈ 82 ±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.
$0.075cache read $0.0188$0.30300K
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 ±9
Terse (38 ±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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
ca.amazon.nova-lite-v1:0 · 🇨🇦 ca
104.7
From 107 benchmarks. Plenty of data behind it.
≈ 82 ±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.
$0.064cache read $0.016$0.256300K
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 ±9
Terse (38 ±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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon-nova/nova-lite-v1
104.7
From 107 benchmarks. Plenty of data behind it.
≈ 82 ±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.
$0.06$0.24300K
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 ±9
Terse (38 ±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
Claude 3 Sonnet
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
regional.anthropic.claude-3-sonnet-20240229-v1:0 · 20240229 · regional
103.7
From 286 benchmarks. Plenty of data behind it.
≈ 76 ±10
Coding IQ 75.7, 95% interval 66–86. 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.
$3.00cache read $0.30$15.00cache write $3.75Not published by the provider
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 measured
119.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3 Sonnet
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
claude-3-sonnet-20240229 · 20240229
103.7
From 286 benchmarks. Plenty of data behind it.
≈ 76 ±10
Coding IQ 75.7, 95% interval 66–86. 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.
$3.00$15.00Not published by the provider
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 measured
119.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3 Sonnet
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
anthropic.claude-3-sonnet-20240229-v1:0 · 20240229
103.7
From 286 benchmarks. Plenty of data behind it.
≈ 76 ±10
Coding IQ 75.7, 95% interval 66–86. 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.
$3.00$15.00Not published by the provider
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 measured
119.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude 2.1We compared the version names in our catalogue.
anthropic.claude-v2
103.6
From 32 benchmarks. Plenty of data behind it.
Not enough data yet$8.00$24.00Not published by the providerNot enough data yetNot measured
117.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Nova Micro
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.nova-micro-v1:0
103.3
From 102 benchmarks. Plenty of data behind it.
Not enough data yet$0.035cache read $0.0088batch $0.0175$0.14batch $0.07128K
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.nova-micro-v1:0:128k · 128k
103.3
From 102 benchmarks. Plenty of data behind it.
Not enough data yet——Not published by the provider
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.nova-micro-v1:0:24k · 24k
103.3
From 102 benchmarks. Plenty of data behind it.
Not enough data yet——Not published by the provider
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
eu.amazon.nova-micro-v1%3A0 · 🇪🇺 eu
103.3
From 102 benchmarks. Plenty of data behind it.
Not enough data yet$0.035cache read $0.0095$0.14cache write $0.04128K
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.amazon.nova-micro-v1%3A0 · 🇺🇸 us
103.3
From 102 benchmarks. Plenty of data behind it.
Not enough data yet$0.035cache read $0.0088batch $0.0175$0.14batch $0.07128K
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
apac.amazon.nova-micro-v1:0 · apac
103.3
From 102 benchmarks. Plenty of data behind it.
Not enough data yet$0.037cache read $0.0093$0.148cache write $0.037128K
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon-nova/nova-micro-v1
103.3
From 102 benchmarks. Plenty of data behind it.
Not enough data yet$0.035$0.14128K
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
Claude 3 Haiku
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
regional.anthropic.claude-3-haiku-20240307-v1:0 · 20240307 · regional
102.7
From 315 benchmarks. Plenty of data behind it.
76 ±10
Coding IQ 75.9, 95% interval 66–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.25$1.25Not published by the provider
33.4
Poor value (33.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
117.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3 Haiku
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
102.7
From 315 benchmarks. Plenty of data behind it.
76 ±10
Coding IQ 75.9, 95% interval 66–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.25$1.25Not published by the provider
33.4
Poor value (33.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
117.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3 Haiku
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0 · 20240307
102.7
From 315 benchmarks. Plenty of data behind it.
76 ±10
Coding IQ 75.9, 95% interval 66–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.30$1.50196K
33.4
Poor value (33.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
117.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3 Haiku
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
claude-3-haiku-20240307 · 20240307
102.7
From 315 benchmarks. Plenty of data behind it.
76 ±10
Coding IQ 75.9, 95% interval 66–86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.25$1.25Not published by the provider
33.4
Poor value (33.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
117.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 2.1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
anthropic.claude-v2:1
101.5
From 85 benchmarks. A fair amount of data behind it.
Not enough data yet$8.00$24.00100K
37.8
Poor value (37.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Llama 3.2 11B Instruct
🇺🇸
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.
meta.llama3-2-11b-instruct-v1:0
100.4
From 10 benchmarks. A fair amount of data behind it.
Not enough data yet$0.16$0.16128KNot enough data yetNot measuredNot measured
Llama 3.2 11B Instruct
🇺🇸
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.
us.meta.llama3-2-11b-instruct-v1:0 · 🇺🇸 us
100.4
From 10 benchmarks. A fair amount of data behind it.
Not enough data yet$0.16$0.16128KNot enough data yetNot measuredNot measured
Llama 2 70B Chat
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
meta.llama2-70b-chat-v1
98.8
From 50 benchmarks. A fair amount of data behind it.
Not enough data yet$1.95$2.564KNot enough data yetNot measuredNot measured
Command R+
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
cohere.command-r-v1:0
97.3
From 220 benchmarks. Plenty of data behind it.
≈ 76 ±11
Coding IQ 75.7, 95% interval 65–87. 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.
$0.50$1.50Not published by the providerNot enough data yetNot measuredNot measured
Command R Plus
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
cohere.command-r-plus-v1:0
96.9
From 196 benchmarks. Plenty of data behind it.
Not enough data yet$3.00$15.00Not published by the provider
21.9
Poor value (21.9). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured

Run by Amazon Web Services

28 listings on this page where Amazon Web Services 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
Nemotron 3 Nano 30B A3B
🇺🇸
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
 Cortecs AI
109.7
From 137 benchmarks. Plenty of data behind it.
91 ±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.
——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
Gemma 3 27B IT
🇺🇸
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.
amazon/google.gemma-3-27b-it
 Eden AI
108.5
From 365 benchmarks. Plenty of data behind it.
73 ±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.
$0.23$0.38128K
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
🇺🇸
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.
amazon/google.gemma-3-27b-it@us · 🇺🇸 us
 Eden AI
108.5
From 365 benchmarks. Plenty of data behind it.
73 ±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.
$0.23$0.38128K
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
🇺🇸
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.
 Hugging Face
108.1
From 278 benchmarks. Plenty of data behind it.
77 ±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.
$0.72$0.72131K
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
🇺🇸
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.
us-east-1
 OpenRouter
108.1
From 278 benchmarks. Plenty of data behind it.
77 ±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.
$0.72$0.72131K
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
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral-large-2402 · 2402
 Cortecs AI
108.0
From 293 benchmarks. Plenty of data behind it.
72 ±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.
——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
Gemma 3 12B IT
🇺🇸
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.
amazon/google.gemma-3-12b-it
 Eden AI
107.6
From 331 benchmarks. Plenty of data behind it.
68 ±19
Coding IQ 68.1, 95% interval 49–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.09$0.29128K
41.7
Poor value (41.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Gemma 3 12B IT
🇺🇸
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.
amazon/google.gemma-3-12b-it@us · 🇺🇸 us
 Eden AI
107.6
From 331 benchmarks. Plenty of data behind it.
68 ±19
Coding IQ 68.1, 95% interval 49–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.09$0.29128K
41.7
Poor value (41.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Ministral 8B
🇫🇷
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 · 2512
 Cortecs AI
107.6
From 73 benchmarks. Plenty of data behind it.
Not enough data yet——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
Llama 3.1 70B Instruct
🇺🇸
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.
 Hugging Face
106.8
From 168 benchmarks. Plenty of data behind it.
≈ 80 ±11
Coding IQ 80.3, 95% interval 69–91. 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.
$0.72$0.72131K
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 measuredNot measured
Llama 3.1 70B Instruct
🇺🇸
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.llama3-1-70b-instruct-v1:0
 Llmgateway
106.8
From 168 benchmarks. Plenty of data behind it.
≈ 80 ±11
Coding IQ 80.3, 95% interval 69–91. 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.
$0.72$0.72Not 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 measuredNot measured
Llama 3.1 70B Instruct
🇺🇸
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.
 OpenRouter
106.8
From 168 benchmarks. Plenty of data behind it.
≈ 80 ±11
Coding IQ 80.3, 95% interval 69–91. 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.
$0.72$0.72131K
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 measuredNot measured
Nova Pro
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
nova-pro-v1
 Cortecs AI
106.4
From 119 benchmarks. Plenty of data behind it.
Not enough data yet——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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/amazon.nova-pro-v1:0@us · 🇺🇸 us
 Eden AI
106.4
From 119 benchmarks. Plenty of data behind it.
Not enough data yet$0.80cache read $0.2175$3.20300K
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/amazon.nova-pro-v1:0
 Eden AI
106.4
From 119 benchmarks. Plenty of data behind it.
Not enough data yet$0.80cache read $0.2175$3.20300K
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/nova-pro-v1 · eu-west-1
 OpenRouter
106.4
From 119 benchmarks. Plenty of data behind it.
Not enough data yet$0.80$3.20300K
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/nova-pro-v1
 OpenRouter
106.4
From 119 benchmarks. Plenty of data behind it.
Not enough data yet$0.80$3.20300K
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
Llama 4 Scout
🇺🇸
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.
meta.llama4-scout-17b-instruct-v1:0
 Llmgateway
106.2
From 347 benchmarks. Plenty of data behind it.
69 ±8
Coding IQ 69.3, 95% interval 61–78. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.17$0.66Not published by the provider
30.3
Poor value (30.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
127.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Nova Lite
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
nova-lite-v1
 Cortecs AI
104.7
From 107 benchmarks. Plenty of data behind it.
≈ 82 ±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.
——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 ±9
Terse (38 ±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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/amazon.nova-lite-v1:0@us · 🇺🇸 us
 Eden AI
104.7
From 107 benchmarks. Plenty of data behind it.
≈ 82 ±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.
$0.06cache read $0.0163$0.24300K
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 ±9
Terse (38 ±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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/amazon.nova-lite-v1:0
 Eden AI
104.7
From 107 benchmarks. Plenty of data behind it.
≈ 82 ±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.
$0.06cache read $0.0163$0.24300K
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 ±9
Terse (38 ±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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/nova-lite-v1 · eu-west-1
 OpenRouter
104.7
From 107 benchmarks. Plenty of data behind it.
≈ 82 ±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.
$0.06$0.24300K
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 ±9
Terse (38 ±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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/nova-lite-v1
 OpenRouter
104.7
From 107 benchmarks. Plenty of data behind it.
≈ 82 ±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.
$0.06$0.24300K
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 ±9
Terse (38 ±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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
nova-micro-v1
 Cortecs AI
103.3
From 102 benchmarks. Plenty of data behind it.
Not enough data yet——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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/amazon.nova-micro-v1:0@us · 🇺🇸 us
 Eden AI
103.3
From 102 benchmarks. Plenty of data behind it.
Not enough data yet$0.035cache read $0.011$0.14128K
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/amazon.nova-micro-v1:0
 Eden AI
103.3
From 102 benchmarks. Plenty of data behind it.
Not enough data yet$0.035cache read $0.011$0.14128K
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/nova-micro-v1 · eu-west-1
 OpenRouter
103.3
From 102 benchmarks. Plenty of data behind it.
Not enough data yet$0.035$0.14128K
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/nova-micro-v1
 OpenRouter
103.3
From 102 benchmarks. Plenty of data behind it.
Not enough data yet$0.035$0.14128K
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