LLM Rankings

Compare models for all prompts (0)

Filter by Category:

Usage Trend

Aggregated token usage over time (static example)

1.

Google: Gemini 2.5 Pro Experimental

Gemini 2.5 Pro Experimental: an AI model designed for...

12.8M views
+1.2%
2.

Microsoft: MAIA OS R2 (free)

MAIA OS R2: A platform for the use of AI in education, R&D, enterprise by...

7.73M views
+0.8%
3.

Llama Guard 3 8B

Llama Guard 3: Large 8.7B parameter model, from Meta for...

9.73M views
+1.6%
4.

DeepSeek: R1 Qwen 1.5B

DeepSeek R1: Small Qwen 1.5B is a global neural language model for...

3.79M views
-0.9%
5.

THUDM: GLM 4 (free)

GLM-4: 2023-10-16 is a 4.3B finetuned open-world...

269M views
+8.5%
6.

DeepSeek: R1 Qwen Owen 1.5B

DeepSeek R1: Qwen Owen 1.5B is an open-source model for...

2.65M views
+0.3%
7.

Google: Gemini 2.5 Flash Preview

Gemini 2.5 Flash: A faster version of the Gemini model with...

8.73M views
+2.7%
8.

Amazon: Nova Micro 1.0

Amazon Nova Micro: A small, efficient model that runs on the smallest...

5.66M views
+1.8%
9.

OpenAI: o3

o3: A powerful multimodal model optimized for speed...

6.57M views
+2.3%
10.

THUDM: GLM Z1 32B (free)

GLM Z1: 2023-10-16 is a larger version of GLM-4...

1.15M views
+1.2%
11.

Google: Gemini 2.5 Flash Preview (thinking)

Gemini 2.5 Flash: A variant of the model focused on reasoning...

32.4M views
+3.7%
12.

Meta: Llama 4 Scout

Llama 4 Scout: The smallest (3.8B) in a collection of models from Meta...

9.23M views
+1.3%
13.

Nous: Hermes 3 70B Instruct

Nous Hermes 3: A powerful 70B parameter model specializing in...

4.48M views
+0.9%
14.

Mistral: Mistral Nemo (free)

Mistral Nemo: An open-source model from Mistral AI built on...

20.1M views
+2.1%
15.

Inflection: Inflection 3 Productivity

Inflection 3: Productivity is optimized for business workflows in a...

4.55M views
+1.5%
16.

Qwen: Qwen2.5-XL 7B Instruct

Qwen2.5-XL: 7B is a medium-sized LLM from the Qwen team with...

3.15M views
+0.8%
17.

Anthropic: Claude v2.1 (self-moderated)

Claude v2.1: Features enhanced reasoning in this variant for...

1.24M views
+1.2%
18.

Mistral: Mistral Small 3.1 24B (free)

Mistral Small 3.1: 24B model is an upgraded version of Mistral Small...

44.7M views
+1.9%
19.

EYA: Qwen2.5 32B

EYA Qwen2.5: 32B is the largest publicly available model in the...

2.35M views
+1.6%
20.

Google: LearnLM 1.5 Pro Experimental (free)

A specialized model of LearnLM 1.5 Pro designed for...

1.78M views
+1.2%
Rankings are based on aggregated usage data. Data updates periodically.