Inkling Falls Short of Frontier Open-Source Models

emollick · x · 2026-07-16

While welcoming the new open-weight model, the author noted that in their tests, Inkling currently performs quite roughly, showing a clear gap compared to frontier Chinese open-source models.

They provided a specific example: the model failed the Lem Test, which almost every frontier model has passed since DeepSeek r1 / Sonnet 3.5.

Related event: New Open-Source Model Inkling Falls Short in Tests(2 posts)→

Original post →

More from Models

Models channel →