ModelBench
Model catalog

Models

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

Compare Export CSV
7 models
Reasoning helicone 8K+
DeepSeek: DeepSeek V3.2 T
Reasoning Tools JSON Open weights

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use

deepseek/deepseek-v3.2 2025-12-01 128K context $0.18/M input $0.35/M output
24 providers
DeepSeek: DeepSeek Reasoner T
Open weights

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

deepseek/deepseek-reasoner 2025-12-01 1M context $0.147/M input $0.295/M output
6 providers
Moonshot AI: Kimi K2 Thinking T
Tools Open weights

Thinking Kimi model for slower research passes, planning, and hard technical questions

moonshotai/kimi-k2-thinking 2025-11-06 262.144K context $0.4/M input $2.5/M output
22 providers
Mistral AI: Mistral Small 3.2 T
Tools Open weights

Efficient Mistral model for fast chat, extraction, and production assistants

mistral/mistral-small-2506 2025-06-20 128K context $0.1/M input $0.3/M output
6 providers
Alibaba Qwen: Qwen3 30B A3B T
Open weights

Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning

alibaba/qwen3-30b-a3b 2025-04-28 131.072K context $0.08/M input $0.29/M output
8 providers
Alibaba Qwen: Qwen3 32B T
Reasoning Tools JSON Open weights

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

alibaba/qwen3-32b 2025-04 131.072K context $0.7/M input $2.8/M output
15 providers
Mistral AI: Mistral Nemo T
Open weights

Efficient Mistral-NVIDIA open model for multilingual chat and local deployment

mistral/mistral-nemo 2024-07-01 128K context $0.15/M input $0.15/M output
11 providers