ModelBench
Model catalog

Models

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

Compare Export CSV
6 models
thinkingmachines Has benchmarks
Ranked by Design Arena: website
DeepSeek: DeepSeek V4.1 Flash 1017 T
Reasoning Tools Open weights 1307.0

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

deepseek/deepseek-v4.1-flash-1017 2026-10-17 1M context $0.15/M input $0.6/M output
33 providers
Moonshot AI: Kimi K2.6 T
Reasoning Tools JSON Open weights 1268.0

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

moonshotai/kimi-k2.6 2026-04-20 262.144K context $0.95/M input $4/M output
69 providers
Thinkingmachines: Inkling T
Reasoning Tools Open weights 1224.0

Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio

thinkingmachines/inkling 2026-07-15 1.04858M context $1.87/M input $4.68/M output
24 providers
NVIDIA: Nemotron 3 Ultra 550B A55B T
Reasoning Tools Open weights 1144.0

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

nvidia/nemotron-3-ultra-550b-a55b 2026-06-04 1M context $0.1/M input $0.1/M output
17 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