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
Image nvidia
Ranked by Agentic Index
Moonshot AI: Kimi K3 T
Reasoning Tools JSON Open weights 50.6

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

moonshotai/kimi-k3 2026-07-16 1.04858M context $3/M input $15/M output
63 providers
Thinkingmachines: Inkling T
Tools JSON Open weights 24.3

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
21 providers
Moonshot AI: Kimi K2.6 T
Reasoning Tools JSON Open weights 22.1

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

moonshotai/kimi-k2.6 2026-04-21 262.144K context $0.95/M input $4/M output
64 providers
StepFun: Step 3.7 Flash T
Reasoning Tools JSON Open weights 21.7

Newer StepFun flash model for faster agents, coding, and multimodal prompts

stepfun/step-3.7-flash 2026-05-29 256K context $0.185/M input $1.11/M output
17 providers
Google: Gemma 4 31B IT T
Reasoning Tools JSON Open weights 6.7

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

google/gemma-4-31b-it 2026-04-02 262.144K context $0.09/M input $0.34/M output
33 providers
Google: Gemma 3 12B IT T
Open weights 0.1

Open multimodal Gemma instruction model for multilingual text generation and image understanding

google/gemma-3-12b-it 2025-03-12 131.072K context $0.05/M input $0.1/M output
8 providers