AI Model Comparison Hub

Factual capabilities and benchmark ratings compared side-by-side. Analyze context windows, licensing configurations, and current token pricing.

Filter Models Database

License Type

Open Weights Proprietary API

Min Context Size: 8k

Sort Catalog By

Select Columns to Compare

Model A

Model B

Model C (Desktop Only)

Specifications	Claude 3.5 Haiku by Anthropic	Qwen 2.5 14B by Alibaba Cloud	Qwen 2.5 72B by Alibaba Cloud	Qwen 2.5 7B by Alibaba Cloud	Mistral Large 2 by Mistral AI	Llama 3.1 405B by Meta	Llama 3.1 70B by Meta	Llama 3.1 8B by Meta	GPT-4o mini by OpenAI	Gemma 2 27B by Google	Gemma 2 9B by Google	Claude 3.5 Sonnet by Anthropic	DeepSeek Coder V2 by DeepSeek	Codestral 22B by Mistral AI	Mistral 7B v0.3 by Mistral AI	Phi-3 Medium by Microsoft	Phi-3 Small by Microsoft	Gemini 1.5 Flash by Google	Gemini 1.5 Pro by Google	GPT-4o by OpenAI	Phi-3 Mini by Microsoft	Mixtral 8x22B by Mistral AI	Command R+ by Cohere	Grok 1.5 by xAI	DBRX by Databricks	Command R by Cohere	Claude 3 Haiku by Anthropic	Claude 3 Opus by Anthropic	Claude 3 Sonnet by Anthropic	Mixtral 8x7B by Mistral AI
Parameters	Confidential	14B	72B	7B	123B	405B	70B	8B	Confidential	27B	9B	Confidential	236B	22B	7.3B	14B	7B	Confidential	Confidential	Confidential	3.8B	141B	104B	Confidential	132B	35B	Confidential	Confidential	Confidential	47B
Context Window	200k tokens	128k tokens	128k tokens	128k tokens	128k tokens	128k tokens	128k tokens	128k tokens	128k tokens	8k tokens	8k tokens	200k tokens	128k tokens	32k tokens	32k tokens	128k tokens	128k tokens	1M tokens	2M tokens	128k tokens	128k tokens	64k tokens	128k tokens	128k tokens	32k tokens	128k tokens	200k tokens	200k tokens	200k tokens	32k tokens
License	Proprietary API	Apache 2.0	Apache 2.0	Apache 2.0	Mistral Research License	Meta Llama 3.1 Community License	Meta Llama 3.1 Community License	Meta Llama 3.1 Community License	Proprietary API	Apache 2.0	Apache 2.0	Proprietary API	DeepSeek License	Mistral AI Research License	Apache 2.0	MIT	MIT	Proprietary API	Proprietary API	Proprietary API	MIT	Apache 2.0	C-UDA License (commercial use with restrictions)	Proprietary API	Databricks Open Source License	CC-BY-NC-4.0	Proprietary API	Proprietary API	Proprietary API	Apache 2.0
Pricing (Input)	$0.25 / M tokens	$0.30 / M tokens	$1.00 / M tokens	$0.10 / M tokens	$2.00 / M tokens	Open Weights (self-host)	Open Weights (self-host)	Open Weights (self-host)	$0.15 / M tokens	Open Weights (self-host)	Open Weights (self-host)	$3.00 / M tokens	$0.14 / M tokens	$1.00 / M tokens	$0.20 / M tokens	$0.50 / M tokens	$0.20 / M tokens	$0.075 / M tokens	$1.25 / M tokens	$2.50 / M tokens	$0.10 / M tokens	$2.00 / M tokens	$2.50 / M tokens	$5.00 / M tokens	$1.50 / M tokens	$0.50 / M tokens	$0.25 / M tokens	$15.00 / M tokens	$3.00 / M tokens	$0.70 / M tokens
Pricing (Output)	$1.25 / M tokens	$0.90 / M tokens	$3.00 / M tokens	$0.30 / M tokens	$6.00 / M tokens	Open Weights (self-host)	Open Weights (self-host)	Open Weights (self-host)	$0.60 / M tokens	Open Weights (self-host)	Open Weights (self-host)	$15.00 / M tokens	$0.28 / M tokens	$3.00 / M tokens	$0.60 / M tokens	$1.50 / M tokens	$0.60 / M tokens	$0.30 / M tokens	$5.00 / M tokens	$10.00 / M tokens	$0.30 / M tokens	$6.00 / M tokens	$10.00 / M tokens	$15.00 / M tokens	$4.50 / M tokens	$1.50 / M tokens	$1.25 / M tokens	$75.00 / M tokens	$15.00 / M tokens	$2.10 / M tokens
Benchmark Ratings
HumanEval	88.1%	72.3%	81.1%	65.4%	76.8%	89%	80.5%	72.6%	87.2%	N/A	N/A	92%	90.2%	81.1%	40.2%	60.1%	52.4%	N/A	N/A	90.2%	58.5%	60.1%	61%	74.1%	70.1%	53%	75.9%	84.9%	73%	40.2%
MMLU	79.5%	79.5%	85%	74%	84%	88.6%	86%	68.4%	82%	81.1%	71.3%	88.7%	78.4%	73.9%	63%	78%	75.3%	78.9%	85.9%	88.7%	68.8%	77.8%	75.7%	81.3%	73.7%	73%	75.2%	86.8%	79%	70.6%

* Benchmark evaluations derived from public datasheets and developer statements. Actual inference capability may differ according to user prompt styles and system configurations.

* Global Disclaimer: Historical figures and software capabilities are for informational reference purposes only. Not technical, professional, legal, or financial advice.