COMPARE.

microsoft

Phi-4-reasoning-plus

Models

Context window

32,768 tokens

Total parameters

14.66 B

Open weights

Yes

Model license

mit

Radar · unrated0/4 core tests · not enough evidence

Unspecified

publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT

Models^*

Maximum output

4,096 tokens^*

Maximum input

8,192 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT

Models^*

Maximum output

4,096 tokens^*

Maximum input

32,768 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

publicai/allenai/Olmo-3-7B-Instruct

Models^*

Maximum output

4,096 tokens^*

Maximum input

32,768 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

publicai/BSC-LT/ALIA-40b-instruct_Q8_0

Models^*

Maximum output

4,096 tokens^*

Maximum input

8,192 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

publicai/BSC-LT/salamandra-7b-instruct-tools-16k

Models^*

Maximum output

4,096 tokens^*

Maximum input

16,384 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

publicai/swiss-ai/apertus-70b-instruct

Models^*

Maximum output

4,096 tokens^*

Maximum input

8,192 tokens^*

Tool calling

No^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

publicai/swiss-ai/apertus-8b-instruct

Models^*

Maximum output

4,096 tokens^*

Maximum input

8,192 tokens^*

Tool calling

No^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

qwen_ai_platform/qwen-flash

Models^*

Maximum output

32,768 tokens^*

Maximum input

997,952 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

qwen_ai_platform/qwen-flash-2025-07-28

Models^*

Maximum output

32,768 tokens^*

Maximum input

997,952 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

qwen_ai_platform/qwen-plus-2025-07-28

Models^*

Maximum output

32,768 tokens^*

Maximum input

997,952 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

qwen_ai_platform/qwen-plus-2025-09-11

Models^*

Maximum output

32,768 tokens^*

Maximum input

997,952 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

qwen_ai_platform/qwen-plus-latest

Models^*

Maximum output

32,768 tokens^*

Maximum input

997,952 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

qwen_ai_platform/qwen3-coder-flash

Models^*

Maximum output

65,536 tokens^*

Maximum input

997,952 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

qwen_ai_platform/qwen3-coder-flash-2025-07-28

Models^*

Maximum output

65,536 tokens^*

Maximum input

997,952 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

qwen_ai_platform/qwen3-coder-plus

Models^*

Maximum output

65,536 tokens^*

Maximum input

997,952 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

qwen_ai_platform/qwen3-coder-plus-2025-07-22

Models^*

Maximum output

65,536 tokens^*

Maximum input

997,952 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

qwen_ai_platform/qwen3-max

Models^*

Maximum output

65,536 tokens^*

Maximum input

258,048 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

qwen_ai_platform/qwen3-max-2026-01-23

Models^*

Maximum output

65,536 tokens^*

Maximum input

258,048 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

qwen_ai_platform/qwen3-max-preview

Models^*

Maximum output

65,536 tokens^*

Maximum input

258,048 tokens^*

Reasoning

Yes^*

Tool calling

Yes^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

qwen_ai_platform/qwen3-next-80b-a3b-instruct

Models^*

Maximum output

65,536 tokens^*

Maximum input

262,144 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

alibaba

Qwen1.5-1.8B-Chat

Models

Context window

32,768 tokens

Total parameters

1.84 B

Open weights

Yes

Model license

other

Radar · unrated0/4 core tests · not enough evidence

alibaba

Qwen1.5-MoE-A2.7B

Models

Context window

8,192 tokens

Total parameters

14.32 B

Open weights

Yes

Model license

other

Radar · unrated0/4 core tests · not enough evidence

alibaba

Qwen2-0.5B

Models

Context window

131,072 tokens

Total parameters

0.49 B

Open weights

Yes

Model license

apache-2.0

Radar · unrated0/4 core tests · not enough evidence