Skip to content

Listings

All listings: Amazon Web Services

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

Sold by Amazon Web Services

60 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
DeepSeek V3.1
🇨🇳
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.
119.6
From 122 benchmarks. Plenty of data behind it.
94 ±8
Coding IQ 94.3, 95% interval 86–103. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.58batch $0.29$1.68batch $0.84128K
44.0
Poor value (44.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
140.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Devstral 2 123b Instruct 2512
🇫🇷
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.devstral-2-123b
119.5
From 25 benchmarks. Plenty of data behind it.
97 ±9
Coding IQ 97.1, 95% interval 88–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.40batch $0.20$2.00batch $1.00256K
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Claude 3.5 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-3-5-sonnet-20240620-v1:0 · 20240620 · regional
119.3
From 546 benchmarks. Plenty of data behind it.
89 ±9
Coding IQ 89.4, 95% interval 81–98. Plenty of data behind it. 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
27.0
Poor value (27.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
130
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3.5 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-3-5-sonnet-20241022-v2:0 · 20241022 · regional
119.3
From 546 benchmarks. Plenty of data behind it.
89 ±9
Coding IQ 89.4, 95% interval 81–98. Plenty of data behind it. 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
27.0
Poor value (27.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
130
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3.5 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.
119.3
From 546 benchmarks. Plenty of data behind it.
89 ±9
Coding IQ 89.4, 95% interval 81–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$15.00Not published by the provider
27.0
Poor value (27.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
130
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3.5 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.
eu.anthropic.claude-3-5-sonnet-20240620-v1:0 · 20240620 · 🇪🇺 eu
119.3
From 546 benchmarks. Plenty of data behind it.
89 ±9
Coding IQ 89.4, 95% interval 81–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00cache read $0.30$15.00cache write $3.75200K
27.0
Poor value (27.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
130
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3.5 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.
eu.anthropic.claude-3-5-sonnet-20241022-v2:0 · 20241022 · 🇪🇺 eu
119.3
From 546 benchmarks. Plenty of data behind it.
89 ±9
Coding IQ 89.4, 95% interval 81–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00cache read $0.30$15.00cache write $3.75200K
27.0
Poor value (27.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
130
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3.5 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.
us.anthropic.claude-3-5-sonnet-20240620-v1:0 · 20240620 · 🇺🇸 us
119.3
From 546 benchmarks. Plenty of data behind it.
89 ±9
Coding IQ 89.4, 95% interval 81–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00cache read $0.30$15.00cache write $3.75200K
27.0
Poor value (27.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
130
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3.5 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.
us.anthropic.claude-3-5-sonnet-20241022-v2:0 · 20241022 · 🇺🇸 us
119.3
From 546 benchmarks. Plenty of data behind it.
89 ±9
Coding IQ 89.4, 95% interval 81–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00cache read $0.30$15.00cache write $3.75200K
27.0
Poor value (27.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
130
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3.5 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.
bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0 · 20240620
119.3
From 546 benchmarks. Plenty of data behind it.
89 ±9
Coding IQ 89.4, 95% interval 81–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.60batch $1.80$18.00batch $9.00200K
27.0
Poor value (27.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
130
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3.5 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-3-5-sonnet-20241022-v2:0 · 20241022
119.3
From 546 benchmarks. Plenty of data behind it.
89 ±9
Coding IQ 89.4, 95% interval 81–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00cache read $0.30$15.00cache write $3.75200K
27.0
Poor value (27.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
130
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3.5 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-3-5-sonnet-20240620 · 20240620
119.3
From 546 benchmarks. Plenty of data behind it.
89 ±9
Coding IQ 89.4, 95% interval 81–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$15.00Not published by the provider
27.0
Poor value (27.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
130
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3.5 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-3-5-sonnet-20241022 · 20241022
119.3
From 546 benchmarks. Plenty of data behind it.
89 ±9
Coding IQ 89.4, 95% interval 81–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$15.00Not published by the provider
27.0
Poor value (27.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
130
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3 Coder
🇨🇳
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.
bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct
119.2
From 84 benchmarks. Plenty of data behind it.
93 ±6
Coding IQ 92.6, 95% interval 87–98. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.45batch $0.225$1.80batch $0.90262K
34.9
Poor value (34.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
39 ±9
Terse (39 ±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
MiniMax M2
🇨🇳
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.
minimax.minimax-m2
118.9
From 111 benchmarks. Plenty of data behind it.
95 ±7
Coding IQ 95.4, 95% interval 88–103. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.30batch $0.15$1.20batch $0.601M
57.8
Good value (57.8). Cheaper per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Mistral Large 3 675b 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.mistral-large-3-675b-instruct
118.9
From 35 benchmarks. A fair amount of data behind it.
Not enough data yet$0.50batch $0.25$1.50batch $0.75256K
53.7
Good value (53.7). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
GPT OSS 120B
🇺🇸
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.
openai.gpt-oss-120b-1:0
118.2
From 424 benchmarks. Plenty of data behind it.
86 ±5
Coding IQ 85.5, 95% interval 80–91. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15batch $0.09$0.60batch $0.36128K
58.4
Good value (58.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 ±11
Terse (37 ±11). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
140.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT OSS 120B
🇺🇸
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/openai.gpt-oss-120b
118.2
From 424 benchmarks. Plenty of data behind it.
86 ±5
Coding IQ 85.5, 95% interval 80–91. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15batch $0.075$0.60batch $0.30131K
58.4
Good value (58.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 ±11
Terse (37 ±11). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
140.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT OSS 120B
🇺🇸
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-gov.openai.gpt-oss-120b-1:0 · 🇺🇸 us-gov
118.2
From 424 benchmarks. Plenty of data behind it.
86 ±5
Coding IQ 85.5, 95% interval 80–91. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.18$0.72128K
58.4
Good value (58.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 ±11
Terse (37 ±11). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
140.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3 Coder Next
🇨🇳
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.
qwen.qwen3-coder-next
118.2
From 27 benchmarks. Plenty of data behind it.
98 ±7
Coding IQ 97.7, 95% interval 90–105. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.50batch $0.25$1.20batch $0.60256K
36.8
Poor value (36.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
54 ±9
Typical (54 ±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.
Not measured
Qwen3 Next 80B A3B Instruct
🇨🇳
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.
bedrock_mantle/qwen.qwen3-next-80b-a3b-instruct
118.1
From 154 benchmarks. Plenty of data behind it.
92 ±11
Coding IQ 91.7, 95% interval 81–102. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.14batch $0.07$1.20batch $0.60256K
47.6
Fair value (47.6). Costs per task about what its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Qwen3 Coder 30B A3B Instruct
🇨🇳
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.
qwen.qwen3-coder-30b-a3b-v1:0
116.2
From 18 benchmarks. A fair amount of data behind it.
Not enough data yet$0.15batch $0.075$0.60batch $0.30262K
54.3
Good value (54.3). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen3 Coder 30B A3B Instruct
🇨🇳
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.
bedrock_mantle/qwen.qwen3-coder-30b-a3b-instruct
116.2
From 18 benchmarks. A fair amount of data behind it.
Not enough data yet$0.15batch $0.075$0.60batch $0.30256K
54.3
Good value (54.3). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
GLM 4.7 Flash
🇨🇳
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.
zai.glm-4.7-flash
116.1
From 186 benchmarks. Plenty of data behind it.
83 ±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.
$0.07batch $0.035$0.40batch $0.20203K
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
Qwen3 32B
🇨🇳
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.
qwen.qwen3-32b-v1:0
115.6
From 234 benchmarks. Plenty of data behind it.
85 ±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.
$0.15batch $0.075$0.60batch $0.3033K
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
🇨🇳
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.
bedrock_mantle/qwen.qwen3-32b
115.6
From 234 benchmarks. Plenty of data behind it.
85 ±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.
$0.15batch $0.075$0.60batch $0.3032K
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
Nova Premier 1.0
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.nova-premier-v1:0
≈ 115
From 13 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$2.50cache read $0.625batch $1.25$12.50batch $6.251M
43.5
Poor value (43.5). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Nova Premier 1.0
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
eu.amazon.nova-premier-v1%3A0 · 🇪🇺 eu
≈ 115
From 13 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$2.50$12.50Not published by the provider
43.5
Poor value (43.5). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Nova Premier 1.0
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.amazon.nova-premier-v1%3A0 · 🇺🇸 us
≈ 115
From 13 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$2.50cache read $0.625$12.50cache write $2.501M
43.5
Poor value (43.5). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Nova Premier 1.0
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon-nova/nova-premier-v1
≈ 115
From 13 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$2.50$12.501M
43.5
Poor value (43.5). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
DeepSeek V3
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionDeepSeek V4We compared the version names in our catalogue.
bedrock/ap-northeast-1/deepseek.v3-v1:0
114.5
From 492 benchmarks. Plenty of data behind it.
85 ±7
Coding IQ 85.3, 95% interval 79–92. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.7017$2.0324128K
43.6
Poor value (43.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
47 ±9
Typical (47 ±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.
135.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Pixtral Large
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral.pixtral-large-2502-v1:0 · 2502
114.2
From 15 benchmarks. Plenty of data behind it.
Not enough data yet$2.00$6.00128K
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
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
eu.mistral.pixtral-large-2502-v1:0 · 2502 · 🇪🇺 eu
114.2
From 15 benchmarks. Plenty of data behind it.
Not enough data yet$2.00$6.00128K
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
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
us.mistral.pixtral-large-2502-v1:0 · 2502 · 🇺🇸 us
114.2
From 15 benchmarks. Plenty of data behind it.
Not enough data yet$2.00$6.00128K
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
Nova 2 Lite
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.nova-2-lite-v1:0
112.6
From 78 benchmarks. Plenty of data behind it.
94 ±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.
$0.30cache read $0.075batch $0.15$2.50batch $1.251M
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon.nova-2-lite-v1:0:256k · 256k
112.6
From 78 benchmarks. Plenty of data behind it.
94 ±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.
——Not 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 measuredNot measured
Nova 2 Lite
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global.amazon.nova-2-lite-v1:0 · global
112.6
From 78 benchmarks. Plenty of data behind it.
94 ±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.
$0.30cache read $0.075batch $0.15$2.50batch $1.251M
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
regional.amazon.nova-2-lite-v1:0 · regional
112.6
From 78 benchmarks. Plenty of data behind it.
94 ±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.
$0.33cache read $0.0825$2.75Not 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 measuredNot measured
Nova 2 Lite
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
apac.amazon.nova-2-lite-v1:0 · apac
112.6
From 78 benchmarks. Plenty of data behind it.
94 ±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.
$0.396cache read $0.099$3.3111M
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
bedrock/eu-north-1/eu.amazon.nova-2-lite-v1:0 · 🇪🇺 eu
112.6
From 78 benchmarks. Plenty of data behind it.
94 ±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.
$0.363cache read $0.0908$2.9921M
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
jp.amazon.nova-2-lite-v1:0 · 🇯🇵 jp
112.6
From 78 benchmarks. Plenty of data behind it.
94 ±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.
$0.396cache read $0.099batch $0.198$3.311cache write $0.396batch $1.65551M
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.amazon.nova-2-lite-v1:0 · 🇺🇸 us
112.6
From 78 benchmarks. Plenty of data behind it.
94 ±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.
$0.33cache read $0.0825batch $0.165$2.75batch $1.3751M
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
Llama 3.1 405B Instruct
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.meta.llama3-1-405b-instruct-v1:0 · 🇺🇸 us
111.8
From 123 benchmarks. Plenty of data behind it.
84 ±9
Coding IQ 84.3, 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.
$2.40$2.40128K
41.9
Poor value (41.9). 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 405B Instruct
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
meta.llama3-1-405b-instruct-v1:0
111.8
From 123 benchmarks. Plenty of data behind it.
84 ±9
Coding IQ 84.3, 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.
$2.40$2.40128K
41.9
Poor value (41.9). 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 Maverick
🇺🇸
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-maverick-17b-instruct-v1:0 · 🇺🇸 us
111.8
From 350 benchmarks. Plenty of data behind it.
78 ±9
Coding IQ 78.1, 95% interval 69–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.24batch $0.12$0.97batch $0.4851M
42.1
Poor value (42.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
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.
132.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT OSS 20b
🇺🇸
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.
openai.gpt-oss-20b-1:0
111.3
From 251 benchmarks. Plenty of data behind it.
88 ±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.
$0.07batch $0.042$0.30batch $0.18128K
48.9
Fair value (48.9). Costs per task about what its benchmark results predict. Plenty of data behind it.
40 ±9
Terse (40 ±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
🇺🇸
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/openai.gpt-oss-20b
111.3
From 251 benchmarks. Plenty of data behind it.
88 ±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.
$0.07batch $0.035$0.30batch $0.15131K
48.9
Fair value (48.9). Costs per task about what its benchmark results predict. Plenty of data behind it.
40 ±9
Terse (40 ±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
🇺🇸
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-gov.openai.gpt-oss-20b-1:0 · 🇺🇸 us-gov
111.3
From 251 benchmarks. Plenty of data behind it.
88 ±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.
$0.084$0.36128K
48.9
Fair value (48.9). Costs per task about what its benchmark results predict. Plenty of data behind it.
40 ±9
Terse (40 ±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
Claude 3 Opus
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
regional.anthropic.claude-3-opus-20240229-v1:0 · 20240229 · regional
111.1
From 307 benchmarks. Plenty of data behind it.
80 ±10
Coding IQ 79.6, 95% interval 70–89. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00$75.00Not published by the provider
38.0
Poor value (38.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
125.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3 Opus
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
eu.anthropic.claude-3-opus-20240229-v1:0 · 20240229 · 🇪🇺 eu
111.1
From 307 benchmarks. Plenty of data behind it.
80 ±10
Coding IQ 79.6, 95% interval 70–89. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00cache read $1.50$75.00cache write $18.75200K
38.0
Poor value (38.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
125.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3 Opus
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
us.anthropic.claude-3-opus-20240229-v1:0 · 20240229 · 🇺🇸 us
111.1
From 307 benchmarks. Plenty of data behind it.
80 ±10
Coding IQ 79.6, 95% interval 70–89. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00cache read $1.50$75.00cache write $18.75200K
38.0
Poor value (38.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
125.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3 Opus
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
anthropic.claude-3-opus-20240229-v1:0 · 20240229
111.1
From 307 benchmarks. Plenty of data behind it.
80 ±10
Coding IQ 79.6, 95% interval 70–89. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00cache read $1.50$75.00cache write $18.75200K
38.0
Poor value (38.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
125.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3 Opus
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
claude-3-opus-20240229 · 20240229
111.1
From 307 benchmarks. Plenty of data behind it.
80 ±10
Coding IQ 79.6, 95% interval 70–89. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00$75.00Not published by the provider
38.0
Poor value (38.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
125.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Embed Multilingual V3.0
🇺🇸
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.
cohere.embed-multilingual-v3
≈ 111
From 29 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.10—512Not enough data yetNot measuredNot measured
Embed Multilingual V3.0
🇺🇸
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.
cohere.embed-multilingual-v3:0:512 · 512
≈ 111
From 29 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Ministral 3 8b 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-3-8b-instruct
110.9
From 14 benchmarks. A fair amount of data behind it.
Not enough data yet$0.15batch $0.07$0.15batch $0.07128KNot enough data yetNot measuredNot measured
Ministral 3 14B 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-3-14b-instruct
110.8
From 15 benchmarks. A fair amount of data behind it.
Not enough data yet$0.20batch $0.10$0.20batch $0.10128KNot enough data yetNot measuredNot measured
Nemotron Nano 9b V2
🇺🇸
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-nano-9b-v2
110.6
From 19 benchmarks. Plenty of data behind it.
Not enough data yet$0.06batch $0.03$0.23batch $0.12128K
52.1
Fair value (52.1). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Nemotron Nano 9b V2
🇺🇸
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-nano-9b-v2:0
110.6
From 19 benchmarks. Plenty of data behind it.
Not enough data yet$0.06$0.23Not published by the provider
52.1
Fair value (52.1). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Nemotron Nano 9b V2
🇺🇸
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-gov.nvidia.nemotron-nano-9b-v2 · 🇺🇸 us-gov
110.6
From 19 benchmarks. Plenty of data behind it.
Not enough data yet$0.072$0.276128K
52.1
Fair value (52.1). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
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
Devstral 2 123b Instruct 2512
🇫🇷
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.
devstral-2512
 Cortecs AI
119.5
From 25 benchmarks. Plenty of data behind it.
97 ±9
Coding IQ 97.1, 95% interval 88–106. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——256K
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
MiniMax M2
🇨🇳
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.
 Cortecs AI
118.9
From 111 benchmarks. Plenty of data behind it.
95 ±7
Coding IQ 95.4, 95% interval 88–103. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——400K
57.8
Good value (57.8). Cheaper per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
GPT OSS 120B
🇺🇸
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.
 Cortecs AI
118.2
From 424 benchmarks. Plenty of data behind it.
86 ±5
Coding IQ 85.5, 95% interval 80–91. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——131K
58.4
Good value (58.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 ±11
Terse (37 ±11). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
140.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT OSS 120B
🇺🇸
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
118.2
From 424 benchmarks. Plenty of data behind it.
86 ±5
Coding IQ 85.5, 95% interval 80–91. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15$0.60131K
58.4
Good value (58.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 ±11
Terse (37 ±11). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
140.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT OSS 120B
🇺🇸
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.
 OpenRouter
118.2
From 424 benchmarks. Plenty of data behind it.
86 ±5
Coding IQ 85.5, 95% interval 80–91. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15$0.60131K
58.4
Good value (58.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 ±11
Terse (37 ±11). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
140.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT OSS 120B
🇺🇸
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.
eu-west-1
 OpenRouter
118.2
From 424 benchmarks. Plenty of data behind it.
86 ±5
Coding IQ 85.5, 95% interval 80–91. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15$0.60131K
58.4
Good value (58.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 ±11
Terse (37 ±11). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
140.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3 Coder Next
🇨🇳
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.
amazon/qwen.qwen3-coder-next
 Eden AI
118.2
From 27 benchmarks. Plenty of data behind it.
98 ±7
Coding IQ 97.7, 95% interval 90–105. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.78$1.86262K
36.8
Poor value (36.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
54 ±9
Typical (54 ±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.
Not measured
Qwen3 Coder 30B A3B Instruct
🇨🇳
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.
 Cortecs AI
116.2
From 18 benchmarks. A fair amount of data behind it.
Not enough data yet——262K
54.3
Good value (54.3). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen3 Coder 30B A3B Instruct
🇨🇳
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.
 Hugging Face
116.2
From 18 benchmarks. A fair amount of data behind it.
Not enough data yet$0.15$0.60262K
54.3
Good value (54.3). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen3 Coder 30B A3B Instruct
🇨🇳
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.
us-west-2
 OpenRouter
116.2
From 18 benchmarks. A fair amount of data behind it.
Not enough data yet$0.15$0.60262K
54.3
Good value (54.3). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
GLM 4.7 Flash
🇨🇳
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.
 Cortecs AI
116.1
From 186 benchmarks. Plenty of data behind it.
83 ±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.
——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
🇨🇳
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.
amazon/zai.glm-4.7-flash@us · 🇺🇸 us
 Eden AI
116.1
From 186 benchmarks. Plenty of data behind it.
83 ±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.
$0.07$0.40203K
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
🇨🇳
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.
amazon/zai.glm-4.7-flash
 Eden AI
116.1
From 186 benchmarks. Plenty of data behind it.
83 ±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.
$0.07$0.40203K
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
🇫🇷
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 · 2512
 Cortecs AI
115.6
From 33 benchmarks. A fair amount of data behind it.
Not enough data yet——256KNot enough data yetNot measuredNot measured
Qwen3 32B
🇨🇳
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.
 Cortecs AI
115.6
From 234 benchmarks. Plenty of data behind it.
85 ±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.
——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
Pixtral Large
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
pixtral-large-2502 · 2502
 Cortecs AI
114.2
From 15 benchmarks. Plenty of data behind it.
Not enough data yet——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
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
amazon/mistral.pixtral-large-2502-v1:0@us · 2502 · 🇺🇸 us
 Eden AI
114.2
From 15 benchmarks. Plenty of data behind it.
Not enough data yet$2.00$6.00128K
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
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
amazon/mistral.pixtral-large-2502-v1:0 · 2502
 Eden AI
114.2
From 15 benchmarks. Plenty of data behind it.
Not enough data yet$2.00$6.00128K
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
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral.pixtral-large-2502-v1:0 · 2502
 Llmgateway
114.2
From 15 benchmarks. Plenty of data behind it.
Not enough data yet$2.00$6.00Not published by the provider
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
🇫🇷
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistralai/pixtral-large-2502 · 2502
 OpenRouter
114.2
From 15 benchmarks. Plenty of data behind it.
Not enough data yet$2.00$6.00128K
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
Nova 2 Lite
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 Cortecs AI
112.6
From 78 benchmarks. Plenty of data behind it.
94 ±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.
——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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/nova-2-lite-v1 · eu-west-1
 OpenRouter
112.6
From 78 benchmarks. Plenty of data behind it.
94 ±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.
$0.30$2.501M
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
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/nova-2-lite-v1
 OpenRouter
112.6
From 78 benchmarks. Plenty of data behind it.
94 ±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.
$0.30$2.501M
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
Llama 4 Maverick
🇺🇸
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-maverick-17b-instruct-v1:0
 Llmgateway
111.8
From 350 benchmarks. Plenty of data behind it.
78 ±9
Coding IQ 78.1, 95% interval 69–87. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.24$0.97Not published by the provider
42.1
Poor value (42.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
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.
132.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT OSS 20b
🇺🇸
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.
 Cortecs AI
111.3
From 251 benchmarks. Plenty of data behind it.
88 ±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.
——131K
48.9
Fair value (48.9). Costs per task about what its benchmark results predict. Plenty of data behind it.
40 ±9
Terse (40 ±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
🇺🇸
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
111.3
From 251 benchmarks. Plenty of data behind it.
88 ±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.
$0.07$0.15131K
48.9
Fair value (48.9). Costs per task about what its benchmark results predict. Plenty of data behind it.
40 ±9
Terse (40 ±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
🇺🇸
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.
 OpenRouter
111.3
From 251 benchmarks. Plenty of data behind it.
88 ±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.
$0.07$0.15131K
48.9
Fair value (48.9). Costs per task about what its benchmark results predict. Plenty of data behind it.
40 ±9
Terse (40 ±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
🇺🇸
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.
eu-west-1
 OpenRouter
111.3
From 251 benchmarks. Plenty of data behind it.
88 ±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.
$0.07$0.15131K
48.9
Fair value (48.9). Costs per task about what its benchmark results predict. Plenty of data behind it.
40 ±9
Terse (40 ±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

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

How this data works