COMPARE.

Unspecified

wandb/zai-org/GLM-5.2

Models^*

Maximum input

1,049,000 tokens^*

Reasoning

Yes^*

API mode

Chat^*

Image input

No^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/bigscience/mt0-xxl

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

Tool calling

No^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/bigscience/mt0-xxl-13b

Models^*

Maximum output

4,096 tokens^*

Maximum input

4,096 tokens^*

Tool calling

No^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/core42/jais-13b-chat

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

Tool calling

No^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/google/flan-t5-xl-3b

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

Tool calling

No^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/ibm/granite-13b-chat-v2

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

Tool calling

No^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/ibm/granite-13b-instruct-v2

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

Tool calling

No^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/ibm/granite-3-3-8b-instruct

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/ibm/granite-4-h-small

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/ibm/granite-guardian-3-2-2b

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

Tool calling

No^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/ibm/granite-guardian-3-3-8b

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

Tool calling

No^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/ibm/granite-ttm-1024-96-r2

Models^*

Maximum output

512 tokens^*

Maximum input

512 tokens^*

Tool calling

No^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/ibm/granite-ttm-1536-96-r2

Models^*

Maximum output

512 tokens^*

Maximum input

512 tokens^*

Tool calling

No^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/ibm/granite-ttm-512-96-r2

Models^*

Maximum output

512 tokens^*

Maximum input

512 tokens^*

Tool calling

No^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/ibm/granite-vision-3-2-2b

Models^*

Maximum output

8,192 tokens^*

Maximum input

8,192 tokens^*

Tool calling

No^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/meta-llama/llama-3-2-11b-vision-instruct

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/meta-llama/llama-3-2-1b-instruct

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/meta-llama/llama-3-2-3b-instruct

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/meta-llama/llama-3-2-90b-vision-instruct

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/meta-llama/llama-3-3-70b-instruct

Models^*

Maximum output

131,072 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/meta-llama/llama-4-maverick-17b

Models^*

Maximum output

8,192 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8

Models^*

Maximum output

8,192 tokens^*

Maximum input

131,072 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/meta-llama/llama-guard-3-11b-vision

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

No^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence

Unspecified

watsonx/mistralai/mistral-medium-2505

Models^*

Maximum output

128,000 tokens^*

Maximum input

128,000 tokens^*

Tool calling

Yes^*

API mode

Chat^*

Radar · unrated0/4 core tests · not enough evidence