ModelBench
Model catalog

Models

Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.

Compare Export CSV
57 models
nvidia 128K+
Meta: Llama 3.2 1B Instruct T
JSON Open weights

Compact instruction-tuned Llama model for multilingual dialogue and on-device assistants

meta/llama-3.2-1b-instruct 2024-09-25 131.072K context $0.01/M input $0.01/M output
7 providers
Meta: Llama-3.2-90B-Vision-Instruct T
Tools Open weights

Large open multimodal Llama model for image reasoning, document QA, and captioning

meta/llama-3.2-90b-vision-instruct 2024-09-25 128K context Input not listed Output not listed
1 provider
Meta: Llama 3.2 3B Instruct T
Tools Open weights

Small instruction-tuned Llama model for multilingual dialogue and agentic retrieval

meta/llama-3.2-3b-instruct 2024-09-25 131.072K context $0.02/M input $0.02/M output
6 providers
NVIDIA: Nemotron Mini 4B Instruct T
Open weights

Compact Nemotron model for efficient reasoning and deployable AI agents

nvidia/nemotron-mini-4b-instruct 2024-08-21 128K context Input not listed Output not listed
1 provider
Abacusai: Dracarys Llama 3.1 70B Instruct T
Open weights

Abacus.AI coding fine-tune of Llama 3.1 70B Instruct

abacusai/dracarys-llama-3.1-70b-instruct 2024-08-14 131.072K context Input not listed Output not listed
1 provider
Meta: Llama-3.1-8B-Instruct T
JSON Open weights

Compact open Llama model for lightweight chat, drafting, and self-hosting

meta/llama-3.1-8b-instruct 2024-07-23 128K context $0.02/M input $0.05/M output
8 providers
Meta: Llama-3.1-70B-Instruct T
Tools JSON Open weights

Open Llama instruction model for multilingual chat, reasoning, and coding

meta/llama-3.1-70b-instruct 2024-07-23 128K context $0.4/M input $0.4/M output
4 providers