Compare AI models

Specifications
Parameters
72B1.5B/7B/72B
Context window
128k4k
These models have no shared benchmark scores.
Overview
CompanyMoonshot AIQwen
Release dateJun 17 2025Sep 19 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi-Dev and Qwen2.5-Math don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2.5-Math shipped 271 days before Kimi-Dev, so benchmark comparisons should account for the intervening progress.

Kimi-Dev has 72B parameters, while Qwen2.5-Math has 1.5B/7B/72B. Context windows are 128k (Kimi-Dev) vs 4k (Qwen2.5-Math).

Direct benchmark comparisons are unavailable — Kimi-Dev and Qwen2.5-Math don't publish scores on any of the same benchmarks.