COMPARE.

Unspecified

ollama/llama2:7b

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ollama/llama3

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ollama/llama3:70b

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ollama/llama3:8b

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ollama/orca-mini

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Text completion^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

ollama/vicuna

Models^*

Maximum output

2,048 tokens^*

Maximum input

2,048 tokens^*

API mode

Text completion^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

omni-moderation-2024-09-26

Models^*

Maximum input

32,768 tokens^*

API mode

Moderation^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

omni-moderation-latest

Models^*

Maximum input

32,768 tokens^*

API mode

Moderation^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/anthropic/claude-sonnet-4-6

Models^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/codellama-34b-instruct

Models^*

Maximum output

16,384 tokens^*

Maximum input

16,384 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/codellama-70b-instruct

Models^*

Maximum output

16,384 tokens^*

Maximum input

16,384 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/google/gemini-3.1-flash-lite

Models^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/google/gemini-3.5-flash

Models^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/llama-2-70b-chat

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/llama-3.1-70b-instruct

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/llama-3.1-8b-instruct

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/mistral-7b-instruct

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/mixtral-8x7b-instruct

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/openai/gpt-5

Models^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/openai/gpt-5.4-mini

Models^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/openai/gpt-5.4-nano

Models^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/perplexity/glm-5.3

Models^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/perplexity/glm-5.3-flash

Models^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/pplx-70b-chat

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence