COMPARE.

Unspecified

nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

Models^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nscale/meta-llama/Llama-3.1-8B-Instruct

Models^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nscale/meta-llama/Llama-3.3-70B-Instruct

Models^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nscale/mistralai/mixtral-8x22b-instruct-v0.1

Models^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nscale/stabilityai/stable-diffusion-xl-base-1.0

Models^*

API mode

Image generation^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2

Models^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3

Models^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

nvidia_nim/ranking/nvidia/llama-3.2-nv-rerankqa-1b-v2

Models^*

API mode

Reranking^*

Radar · unrated0/4 core tests · not enough evidence

microsoft

OmniParser

Models

Open weights

Yes

Model license

mit

Architecture

blip-2

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/anthropic/claude-fable-5-1

Models^*

API mode

Responses API^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/anthropic/claude-opus-5-5

Models^*

API mode

Responses API^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/google/gemini-2.5-pro

Models^*

Reasoning

No^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/google/gemini-3-pro-preview

Models^*

Reasoning

No^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/openai/gpt-5-nano

Models^*

API mode

Responses API^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/openai/gpt-5.3-codex

Models^*

API mode

Responses API^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/perplexity/deepseek-v4-pro-0813

Models^*

API mode

Responses API^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/pplx-decider-flash-latest

Models^*

Maximum input

262,144 tokens^*

API mode

Evaluation service^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/pplx-decider-flash-v1.2

Models^*

Maximum input

262,144 tokens^*

API mode

Evaluation service^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/pplx-decider-latest

Models^*

Maximum input

262,144 tokens^*

API mode

Evaluation service^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/pplx-decider-v1-27b

Models^*

Maximum input

262,144 tokens^*

API mode

Evaluation service^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/pplx-decider-v1.1-27b

Models^*

Maximum input

262,144 tokens^*

API mode

Evaluation service^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/pplx-decider-v1.2

Models^*

Maximum input

262,144 tokens^*

API mode

Evaluation service^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/xai/grok-4-1-fast-non-reasoning

Models^*

Reasoning

No^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

snowflake/gemma-7b

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,000 tokens^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence