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
crusoe Open weights
Ranked by Coding Index
Moonshot AI: Kimi K2.6 T
Reasoning Tools JSON Open weights 61.8

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
Google: Gemma 4 31B IT T
Reasoning Tools JSON Open weights 43.4

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

google/gemma-4-31b-it 2026-04-02 262.144K context $0.1/M input $0.3/M output
37 providers
NVIDIA: Nemotron 3 Super 120B A12B T
Reasoning Open weights 37.7

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

nvidia/nemotron-3-super-120b-a12b 2026-03-11 262.144K context $0.05/M input $0.25/M output
17 providers
OpenAI: GPT OSS 120B T
Reasoning Tools Open weights 30.4

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 $0.15/M output
62 providers
DeepSeek: DeepSeek V3 0324 T
Tools Open weights 21.2

DeepSeek chat model for instruction following, coding, and analysis

deepseek/deepseek-chat-v3-0324 2025-03-24 163.84K context $0.2/M input $0.8/M output
8 providers
NVIDIA: Nemotron 3 Nano 30B A3B T
Open weights 14.4

Small Nemotron 3 MoE for efficient coding, math, and long-context agents

nvidia/nemotron-3-nano-30b-a3b 2025-12-15 262.144K context $0.05/M input $0.2/M output
14 providers