ModelBench
Model catalog

Models

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

Compare Export CSV
4 models
merge-gateway Open weights
Ranked by Aider Polyglot
DeepSeek: DeepSeek-R1 T
Reasoning Tools JSON Open weights 56.9

Classic open reasoning model for transparent math, coding, and deliberate problem solving

deepseek/deepseek-r1 2025-01-20 128K context $0.58/M input $2.319/M output
16 providers
Alibaba Qwen: Qwen3 32B T
Reasoning Tools Open weights 40.0

Dense open Qwen model for self-hosted chat, reasoning, and coding

alibaba/qwen3-32b 2025-04-28 131.072K context $0.7/M input $2.8/M output
16 providers
Cohere: Command A T
Reasoning Tools Open weights 12.0

Cohere command model for multilingual enterprise agents, tools, and chat

cohere/command-a-03-2025 2025-03-13 256K context $2.5/M input $10/M output
6 providers
Mistral AI: Codestral (latest) T
Tools JSON Open weights 11.1

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