Compare AI models

Specifications
Parameters
72B8B/43B
Context window
128k4k
These models have no shared benchmark scores.
Overview
CompanyMoonshot AINVIDIA
Release dateJun 17 2025Mar 21 2023
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Kimi-Dev and NeMo GPT (8B/43B) don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. NeMo GPT (8B/43B) shipped 819 days before Kimi-Dev, so benchmark comparisons should account for the intervening progress.

Kimi-Dev has 72B parameters, while NeMo GPT (8B/43B) has 8B/43B. Context windows are 128k (Kimi-Dev) vs 4k (NeMo GPT (8B/43B)). Kimi-Dev is open weight, while NeMo GPT (8B/43B) is closed.

Direct benchmark comparisons are unavailable — Kimi-Dev and NeMo GPT (8B/43B) don't publish scores on any of the same benchmarks.