Compare AI models

Specifications
Parameters
1T—
Context window
256k—
API pricing
Cheapest input
$0.49AtlasCloud—
Cheapest output
$2.50AtlasCloud—
$223AtlasCloud · int4—
Benchmarks
MMLU-Pro
87.1%72%
Overview
CompanyMoonshot AISpaceXSI
Release dateJan 27 2026Aug 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Kimi K2.5 leads Grok‑2 mini on 1 of the 1 benchmark they both report (MMLU-Pro). Grok‑2 mini shipped 532 days before Kimi K2.5, so benchmark comparisons should account for the intervening progress.

Kimi K2.5 is open weight, while Grok‑2 mini is closed.

On MMLU-Pro, Kimi K2.5 leads at 87.1% vs Grok‑2 mini at 72%.