Compare AI models

Specifications
Parameters
1T—
Context window
256k1M
API pricing
Cheapest input
$0.49AtlasCloud—
Cheapest output
$2.50AtlasCloud—
$223AtlasCloud · int4—
Benchmarks
LiveCodeBench
85%37.8%
MMLU-Pro
87.1%64.5%
Overview
CompanyMoonshot AIQwen
Release dateJan 27 2026Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Kimi K2.5 leads Qwen2.5-Turbo (1M) on 2 of the 2 benchmarks they both report (LiveCodeBench, MMLU-Pro). Qwen2.5-Turbo (1M) shipped 438 days before Kimi K2.5, so benchmark comparisons should account for the intervening progress.

Context windows are 256k (Kimi K2.5) vs 1M (Qwen2.5-Turbo (1M)). Kimi K2.5 is open weight, while Qwen2.5-Turbo (1M) is closed.

On LiveCodeBench, Kimi K2.5 leads at 85% vs Qwen2.5-Turbo (1M) at 37.8%. On MMLU-Pro, Kimi K2.5 leads at 87.1% vs Qwen2.5-Turbo (1M) at 64.5%.