ModelBench
Model catalog

Models

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

Compare Export CSV
5 models
google-vertex Open weights
Ranked by Design Arena: website
DeepSeek: DeepSeek V3.2 T
Reasoning Tools JSON Open weights 1173.0

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

deepseek/deepseek-v3.2 2025-12-01 128K context $0.209/M input $0.31/M output
28 providers
DeepSeek: DeepSeek V3.1 T
Tools JSON Open weights 1122.0

DeepSeek chat model for instruction following, coding, and analysis

deepseek/deepseek-chat-v3.1 2025-08-21 163.84K context $0.19/M input $0.79/M output
10 providers
Moonshot AI: Kimi K2 Thinking T
Reasoning Tools JSON Open weights 1113.0

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
23 providers
OpenAI: GPT OSS 120B T
Reasoning Tools JSON Open weights 966.0

Open GPT reasoning model for self-hosted agents and controllable deployments

openai/gpt-oss-120b 2025-08-05 131.072K context $0.03/M input $0.17/M output
62 providers
OpenAI: GPT OSS 20B T
Reasoning Tools JSON Open weights 852.0

Open GPT reasoning model for self-hosted agents and controllable deployments

openai/gpt-oss-20b 2025-08-05 131.072K context $0.018/M input $0.09/M output
39 providers