Compare AI models

Specifications
Parameters
1T—
Context window
256k—
API pricing
Cheapest input
$0.60Novita—
Cheapest output
$2.50Novita—
$245Novita · bf16—
Benchmarks
MMLU-Pro
84.6%72%
Overview
CompanyMoonshot AISpaceXSI
Release dateNov 6 2025Aug 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Kimi K2 Thinking leads Grok‑2 mini on 1 of the 1 benchmark they both report (MMLU-Pro). Grok‑2 mini shipped 450 days before Kimi K2 Thinking, so benchmark comparisons should account for the intervening progress.

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

On MMLU-Pro, Kimi K2 Thinking leads at 84.6% vs Grok‑2 mini at 72%.