Skip to content

Listings

All listings: OpenRouter

Every listing for the models on page 13 of 26 of OpenRouter, including each model's other versions and routes. Back to OpenRouter

Sold by OpenRouter

83 listings on this page sold by OpenRouter.

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
GPT-4o mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
108.6
From 478 benchmarks. Plenty of data behind it.
72Β Β±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.075$0.60128K
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4o mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
openai/gpt-4o-mini-2024-07-18 Β· 2024-07-18
108.6
From 478 benchmarks. Plenty of data behind it.
72Β Β±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.075$0.60128K
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4o mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
openai/gpt-4o-mini:batch Β· batch
108.6
From 478 benchmarks. Plenty of data behind it.
72Β Β±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.075cache read $0.0375$0.30128K
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4o mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Inference by Microsoft Azure
108.6
From 478 benchmarks. Plenty of data behind it.
72Β Β±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.075$0.60128K
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4o mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Inference by OpenAI
108.6
From 478 benchmarks. Plenty of data behind it.
72Β Β±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.075$0.60128K
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-4o mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
openai/gpt-4o-mini-2024-07-18 Β· 2024-07-18
Inference by OpenAI
108.6
From 478 benchmarks. Plenty of data behind it.
72Β Β±18
Coding IQ 71.8, 95% interval 54–90. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.075$0.60128K
22.1
Poor value (22.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
123.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemma 3 27B IT
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
google/gemma-3-27b-it:free Β· free
108.5
From 365 benchmarks. Plenty of data behind it.
73Β Β±8
Coding IQ 72.7, 95% interval 65–81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.00$0.00Not published by the provider
46.2
Poor value (46.2). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
127.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemma 3 27B IT
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
108.5
From 365 benchmarks. Plenty of data behind it.
73Β Β±8
Coding IQ 72.7, 95% interval 65–81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.08cache read $0.04$0.45131K
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fp8
Inference by DeepInfra
108.5
From 365 benchmarks. Plenty of data behind it.
73Β Β±8
Coding IQ 72.7, 95% interval 65–81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.08$0.16131K
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fp8/flex Β· fp8
Inference by DeepInfra
108.5
From 365 benchmarks. Plenty of data behind it.
73Β Β±8
Coding IQ 72.7, 95% interval 65–81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.064$0.128131K
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fp8/priority Β· fp8
Inference by DeepInfra
108.5
From 365 benchmarks. Plenty of data behind it.
73Β Β±8
Coding IQ 72.7, 95% interval 65–81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.12$0.24131K
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fp8
Inference by Nebius AI Studio
108.5
From 365 benchmarks. Plenty of data behind it.
73Β Β±8
Coding IQ 72.7, 95% interval 65–81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10cache read $0.04$0.30110K
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fp8
Inference by Nextbit
108.5
From 365 benchmarks. Plenty of data behind it.
73Β Β±8
Coding IQ 72.7, 95% interval 65–81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.08cache read $0.04$0.35131K
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fp8
Inference by Parasail
108.5
From 365 benchmarks. Plenty of data behind it.
73Β Β±8
Coding IQ 72.7, 95% interval 65–81. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.08cache read $0.04$0.45131K
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 70B Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionLlama 3.3 70B InstructWe compared release dates and version names in our catalogue.
108.2
From 199 benchmarks. Plenty of data behind it.
β‰ˆ 77Β Β±11
Coding IQ 76.5, 95% interval 66–87. 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.
$0.30$0.40Not published by the provider
49.9
Fair value (49.9). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Llama 3.3 70B Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
meta-llama/llama-3.3-70b-instruct:free Β· free
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±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.
$0.00$0.00Not published by the provider
31.6
Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
126.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Llama 3.3 70B Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±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.
$0.71$0.71128K
31.6
Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
126.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Llama 3.3 70B Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fp8
Inference by Akash
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±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.
$0.20cache read $0.10$0.52131K
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
us-east-1
Inference by Amazon Web Services
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fp8
Inference by Cloudflare Workers AI
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±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.
$0.293$2.25324K
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fp16
Inference by Coreweave
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±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.
$0.71$0.71128K
31.6
Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
126.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Llama 3.3 70B Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
turbo Β· fp8
Inference by DeepInfra
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±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.
$0.10$0.32131K
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Inference by Google
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±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$0.72128K
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
us-central1
Inference by Google
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±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$0.72128K
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Inference by Groq
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±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.
$0.59cache read $0.295$0.79131K
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fp8
Inference by Parasail
108.1
From 278 benchmarks. Plenty of data behind it.
77Β Β±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.
$0.22cache read $0.11$0.50131K
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
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistralai/mistral-large-2411 Β· 2411
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±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$6.00Not published by the provider
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±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.
$2.00cache read $0.20$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
Mistral Large
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistralai/mistral-large-2407 Β· 2407
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±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.
$2.00cache read $0.20$6.00131K
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
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Inference by Mistral AI
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±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.
$2.00cache read $0.20$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
Mistral Large
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistralai/mistral-large-2407 Β· 2407
Inference by Mistral AI
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±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.
$2.00cache read $0.20$6.00131K
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
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistralai/mistral-large-2407 Β· eu+2407
Inference by Mistral AI
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±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.
$2.20cache read $0.22$6.60131K
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
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistralai/mistral-large-2407 Β· zdr+2407
Inference by Mistral AI
108.0
From 293 benchmarks. Plenty of data behind it.
72Β Β±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.
$2.00cache read $0.20$6.00131K
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
WizardLM 2 8x22B
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
β‰ˆ 108
From 9 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.50$0.50Not published by the provider
43.8
Poor value (43.8). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20$0.60Not published by the provider
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/mistral-small-2603 Β· 2603
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.60262K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/mistral-small-2603 Β· eu+2603
Inference by Mistral AI
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.165cache read $0.0165$0.66262K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/mistral-small-2603 Β· us+2603
Inference by Mistral AI
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.165cache read $0.0165$0.66262K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/mistral-small-2603 Β· zdr+2603
Inference by Mistral AI
107.8
From 316 benchmarks. Plenty of data behind it.
78Β Β±10
Coding IQ 78.4, 95% interval 68–89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.60262K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Gemma 3 12B IT
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionGemma 4 12B ItWe compared release dates and version names in our catalogue.
google/gemma-3-12b-it:free Β· free
107.6
From 331 benchmarks. Plenty of data behind it.
68Β Β±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.
$0.00$0.00Not published by the provider
41.7
Poor value (41.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Gemma 3 12B IT
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionGemma 4 12B ItWe compared release dates and version names in our catalogue.
107.6
From 331 benchmarks. Plenty of data behind it.
68Β Β±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.
$0.05$0.15131K
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionGemma 4 12B ItWe compared release dates and version names in our catalogue.
bf16
Inference by DeepInfra
107.6
From 331 benchmarks. Plenty of data behind it.
68Β Β±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.
$0.05$0.15131K
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionGemma 4 12B ItWe compared release dates and version names in our catalogue.
bf16/flex Β· bf16
Inference by DeepInfra
107.6
From 331 benchmarks. Plenty of data behind it.
68Β Β±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.
$0.04$0.12131K
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionGemma 4 12B ItWe compared release dates and version names in our catalogue.
bf16/priority Β· bf16
Inference by DeepInfra
107.6
From 331 benchmarks. Plenty of data behind it.
68Β Β±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.
$0.075$0.225131K
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionGemma 4 12B ItWe compared release dates and version names in our catalogue.
int4
Inference by Nextbit
107.6
From 331 benchmarks. Plenty of data behind it.
68Β Β±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.
$0.35cache read $0.05$0.45131K
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
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
107.6
From 73 benchmarks. Plenty of data behind it.
Not enough data yet$0.10$0.10Not published by the provider
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
Ministral 8B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/ministral-8b-2512 Β· 2512
107.6
From 73 benchmarks. Plenty of data behind it.
Not enough data yet$0.15cache read $0.015$0.15262K
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
Ministral 8B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/ministral-8b-2512 Β· eu+2512
Inference by Mistral AI
107.6
From 73 benchmarks. Plenty of data behind it.
Not enough data yet$0.165cache read $0.0165$0.165262K
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
Ministral 8B
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/ministral-8b-2512 Β· zdr+2512
Inference by Mistral AI
107.6
From 73 benchmarks. Plenty of data behind it.
Not enough data yet$0.15cache read $0.015$0.15262K
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
ERNIE 4.5 21B A3B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
β‰ˆ 107
From 37 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.07$0.28Not published by the provider
46.6
Poor value (46.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
ERNIE 4.5 21B A3B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
baidu/ernie-4.5-21b-a3b-thinking Β· thinking
β‰ˆ 107
From 37 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$0.07$0.28Not published by the provider
46.6
Poor value (46.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Mixtral 8x22B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
107.4
From 7 benchmarks. A fair amount of data behind it.
Not enough data yet$2.00cache read $0.20$6.0066KNot enough data yetNot measuredNot measured
Mixtral 8x22B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
eu
Inference by Mistral AI
107.4
From 7 benchmarks. A fair amount of data behind it.
Not enough data yet$2.20cache read $0.22$6.6066KNot enough data yetNot measuredNot measured
Mixtral 8x22B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
zdr
Inference by Mistral AI
107.4
From 7 benchmarks. A fair amount of data behind it.
Not enough data yet$2.00cache read $0.20$6.0066KNot enough data yetNot measuredNot measured
Qwen2 72B Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen2.5 72B InstructWe compared release dates and version names in our catalogue.
107.3
From 265 benchmarks. Plenty of data behind it.
β‰ˆ 76Β Β±11
Coding IQ 76.2, 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.
$0.90$0.90Not published by the provider
34.3
Poor value (34.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Grok Beta
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
107.2
From 11 benchmarks. A fair amount of data behind it.
β‰ˆ 78Β Β±11stale
Coding IQ 77.6, 95% interval 66–89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old.
$5.00$15.00Not published by the providerNot enough data yetNot measuredNot measured
DeepSeek R1 Distill Qwen 32B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
107.1
From 40 benchmarks. Plenty of data behind it.
β‰ˆ 81Β Β±12stale
Coding IQ 80.5, 95% interval 68–93. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old.
$0.12$0.18Not published by the providerNot enough data yetNot measuredNot measured
DeepSeek R1 Distill Qwen 14B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
107.0
From 24 benchmarks. Plenty of data behind it.
Not enough data yet$0.15$0.15Not published by the providerNot enough data yetNot measuredNot measured
Llama 3.1 70B Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionLlama 3.3 70B InstructWe compared release dates and version names in our catalogue.
106.8
From 168 benchmarks. Plenty of data behind it.
β‰ˆ 80Β Β±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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionLlama 3.3 70B InstructWe compared release dates and version names in our catalogue.
Inference by Amazon Web Services
106.8
From 168 benchmarks. Plenty of data behind it.
β‰ˆ 80Β Β±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
GPT 4 1106 Preview
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.5-previewWe compared the version names in our catalogue.
β‰ˆ 107
From 72 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$10.00$30.00Not published by the providerNot enough data yetNot measuredNot measured
Nova Pro
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/nova-pro-v1 Β· eu-west-1
Inference by Amazon Web Services
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
amazon/nova-pro-v1
Inference by Amazon Web Services
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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
meta-llama/llama-4-scout:free Β· free
106.3
From 347 benchmarks. Plenty of data behind it.
69Β Β±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.
$0.00$0.00Not 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
Llama 4 Scout
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
106.3
From 347 benchmarks. Plenty of data behind it.
69Β Β±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.
$0.10$0.30328K
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
Llama 4 Scout
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fp8
Inference by DeepInfra
106.3
From 347 benchmarks. Plenty of data behind it.
69Β Β±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.
$0.10$0.30328K
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
Llama 4 Scout
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fp8/flex Β· fp8
Inference by DeepInfra
106.3
From 347 benchmarks. Plenty of data behind it.
69Β Β±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.
$0.08$0.24328K
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
Llama 4 Scout
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
fp8/priority Β· fp8
Inference by DeepInfra
106.3
From 347 benchmarks. Plenty of data behind it.
69Β Β±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.
$0.15$0.45328K
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
Llama 4 Scout
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
us-east5
Inference by Google
106.3
From 347 benchmarks. Plenty of data behind it.
69Β Β±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.
$0.25$0.701.3M
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
Mistral Small 24B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/mistral-small-24b-instruct-2501:free Β· free+2501
106.3
From 74 benchmarks. Plenty of data behind it.
β‰ˆ 78Β Β±11
Coding IQ 77.9, 95% interval 67–89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
β€”β€”Not published by the providerNot enough data yetNot measuredNot measured
Mistral Small 24B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/mistral-small-24b-instruct-2501 Β· 2501
106.3
From 74 benchmarks. Plenty of data behind it.
β‰ˆ 78Β Β±11
Coding IQ 77.9, 95% interval 67–89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.05$0.0833KNot enough data yetNot measuredNot measured
Mistral Small 24B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/mistral-small-24b-instruct-2501 Β· fp8/flex+2501 Β· fp8
Inference by DeepInfra
106.3
From 74 benchmarks. Plenty of data behind it.
β‰ˆ 78Β Β±11
Coding IQ 77.9, 95% interval 67–89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.04$0.06433KNot enough data yetNot measuredNot measured
Mistral Small 24B Instruct
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
mistralai/mistral-small-24b-instruct-2501 Β· fp8+2501 Β· fp8
Inference by DeepInfra
106.3
From 74 benchmarks. Plenty of data behind it.
β‰ˆ 78Β Β±11
Coding IQ 77.9, 95% interval 67–89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.05$0.0833KNot enough data yetNot measuredNot measured
Qwen 2.5 Coder 32B Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
qwen/qwen-2.5-coder-32b-instruct:free Β· free
106.3
From 104 benchmarks. Plenty of data behind it.
81Β Β±9
Coding IQ 80.7, 95% interval 72–89. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.00$0.00Not published by the provider
50.7
Fair value (50.7). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen 2.5 Coder 32B Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
106.3
From 104 benchmarks. Plenty of data behind it.
81Β Β±9
Coding IQ 80.7, 95% interval 72–89. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.66$1.0033K
50.7
Fair value (50.7). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen 2.5 Coder 32B Instruct
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Inference by Cloudflare Workers AI
106.3
From 104 benchmarks. Plenty of data behind it.
81Β Β±9
Coding IQ 80.7, 95% interval 72–89. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.66$1.0033K
50.7
Fair value (50.7). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Gemini 1.5 Flash-8B
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gemini-flash-1.5-8b
106.1
From 50 benchmarks. Plenty of data behind it.
Not enough data yet$0.0375cache read $0.01$0.15cache write $0.0583Not published by the providerNot enough data yetNot measuredNot measured
Llama 3.2 90B Vision Instruct
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
106.1
From 54 benchmarks. Plenty of data behind it.
Not enough data yet$1.20$1.20Not published by the provider
57.0
Good value (57.0). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Phi 4
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
105.9
From 144 benchmarks. Plenty of data behind it.
β‰ˆ 78Β Β±11
Coding IQ 77.6, 95% interval 66–89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.07$0.1416K
51.2
Fair value (51.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
129.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Phi 4
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
bf16
Inference by DeepInfra
105.9
From 144 benchmarks. Plenty of data behind it.
β‰ˆ 78Β Β±11
Coding IQ 77.6, 95% interval 66–89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.07$0.144K
51.2
Fair value (51.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
129.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Phi 4
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
bf16/flex Β· bf16
Inference by DeepInfra
105.9
From 144 benchmarks. Plenty of data behind it.
β‰ˆ 78Β Β±11
Coding IQ 77.6, 95% interval 66–89. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.056$0.11216K
51.2
Fair value (51.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
129.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3 4B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen3.5 4BWe compared release dates and version names in our catalogue.
qwen/qwen3-4b:free Β· free
105.8
From 116 benchmarks. Plenty of data behind it.
β‰ˆ 78Β Β±9
Coding IQ 78.4, 95% interval 69–88. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.00$0.00Not published by the provider
32.9
Poor value (32.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured

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

How this data works