ModelBench
Model catalog

Models

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

Compare Export CSV
55 models
Open weights
Ranked by Intelligence Index
Rekaai: Reka Flash 3 T
Reasoning JSON Open weights 6.4

Efficient model for low-latency assistance, extraction, and routine automation

rekaai/reka-flash-3 2025-03-10 65.536K context $0.1/M input $0.2/M output
3 providers
Microsoft: Microsoft: Phi 4 T
Open weights 5.9

[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...

microsoft/phi-4 16.384K context $0.07/M input $0.14/M output
Google: Gemma 3 27B IT T
Open weights 4.9

Largest open Gemma 3 instruction model for multilingual text generation and visual understanding

google/gemma-3-27b-it 2025-03-12 131.072K context $0.08/M input $0.35/M output
13 providers
Google: Gemma 3 4B IT T
Open weights 4.8

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

google/gemma-3-4b-it 2025-03-12 131.072K context $0.04/M input $0.05/M output
9 providers
Google: Gemma 3 12B IT T
Open weights 3.8

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

google/gemma-3-12b-it 2025-03-12 131.072K context $0.04/M input $0.12/M output
10 providers