COMPARE.

allenai

olmOCR-7B-0825

Models

Context window

128,000 tokens

Open weights

Yes

Model license

apache-2.0

Checkpoint tensor payload

15.45 GiB

Radar · unrated0/4 core tests · not enough evidence

allenai

OLMoE-1B-7B-0125

Models

Context window

4,096 tokens

Open weights

Yes

Model license

apache-2.0

Checkpoint tensor payload

25.78 GiB

Radar · unrated0/4 core tests · not enough evidence

allenai

OLMoE-1B-7B-0125-DPO

Models

Context window

4,096 tokens

Open weights

Yes

Model license

apache-2.0

Checkpoint tensor payload

12.89 GiB

Radar · unrated0/4 core tests · not enough evidence

allenai

OLMoE-1B-7B-0125-Instruct

Models

Context window

4,096 tokens

Open weights

Yes

Model license

apache-2.0

Checkpoint tensor payload

12.89 GiB

Radar · unrated0/4 core tests · not enough evidence

allenai

OLMoE-1B-7B-0924

Models

Context window

4,096 tokens

Open weights

Yes

Model license

apache-2.0

Checkpoint tensor payload

12.89 GiB

Radar · unrated0/4 core tests · not enough evidence

allenai

OLMoE-1B-7B-0924-Instruct

Models

Context window

4,096 tokens

Open weights

Yes

Model license

apache-2.0

Checkpoint tensor payload

12.89 GiB

Radar · unrated0/4 core tests · not enough evidence

microsoft

OptiMind-SFT

Models

Context window

131,072 tokens

Open weights

Yes

Model license

mit

Checkpoint tensor payload

38.96 GiB

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/anthropic/claude-haiku-4-5

Models^*

Reasoning

No^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/anthropic/claude-haiku-5-5

Models^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/anthropic/claude-opus-4-8

Models^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/anthropic/claude-sonnet-4-5

Models^*

Reasoning

No^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/anthropic/claude-sonnet-5

Models^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/anthropic/claude-sonnet-5-5

Models^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/google/gemini-3-flash-preview

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-3.5-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-3.6-flash

Models^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/google/gemini-3.7-flash

Models^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/openai/gpt-5-mini

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-5.1

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-5.2

Models^*

Reasoning

Yes^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/openai/gpt-6-luna

Models^*

API mode

Responses API^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/openai/gpt-6-sol

Models^*

API mode

Responses API^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/openai/gpt-6.1-sol

Models^*

API mode

Responses API^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

perplexity/perplexity/deepseek-v4-flash-0731

Models^*

Reasoning

Yes^*

Tool calling

Yes^*

API mode

Responses API^*

Web search

Yes^*

Radar · unrated0/4 core tests · not enough evidence