ModelBench
Model catalog

Models

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

Compare Export CSV
108 models
Open weights Has benchmarks
Meta: Llama-3.3-70B-Instruct T
Tools JSON Open weights

Popular open Llama workhorse for multilingual chat, coding, and self-hosting

meta/llama-3.3-70b-instruct 2024-12-06 128K context $0.1/M input $0.32/M output
29 providers
Mistral AI: Mistral Large 2.1 T
Open weights

Flagship Mistral model for advanced reasoning, coding, and multilingual work

mistral/mistral-large-2411 2024-11-18 131.072K context Input not listed Output not listed
2 providers
Nousresearch: Hermes 3 70B Instruct T
JSON Open weights

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

nousresearch/hermes-3-llama-3.1-70b 2024-08-18 131.072K context $0.7/M input $0.7/M output
3 providers
Nousresearch: Hermes 3 405B Instruct T
JSON Open weights

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

nousresearch/hermes-3-llama-3.1-405b 2024-08-16 131.072K context $1/M input $1/M output
3 providers
Mistral AI: Codestral (latest) T
Tools Open weights

Mistral code model for completions, refactors, and developer IDE workflows

mistral/codestral-latest 2024-05-29 256K context $0.3/M input $0.9/M output
4 providers
IBM: IBM: Granite 4.1 8B T
Open weights

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...

ibm-granite/granite-4.1-8b 131.072K context $0.05/M input $0.1/M output
Microsoft: Microsoft: Phi 4 T
Open weights

[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...

microsoft/phi-4 16.384K context $0.07/M input $0.14/M output
IBM: IBM: Granite 4.2 8B T
Open weights

Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...

ibm-granite/granite-4.2-8b 131.072K context $0.06/M input $0.25/M output