Compare AI models

Specifications
Parameters
1T49B
Context window
256k128k
API pricing
Cheapest input
$0.60Novita—
Cheapest output
$2.50Novita—
$245Novita · bf16—
Benchmarks
LiveCodeBench
83.1%73.58%
Humanity's Last Exam · text only, no tools
23.9%7.64%
AIME 2025
94.5%82.71%
GPQA Diamond
84.5%71.97%
MMLU-Pro
84.6%79.53%
Overview
CompanyMoonshot AINVIDIA
Release dateNov 6 2025Jul 25 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2 Thinking leads Llama Nemotron Super 49B v1.5 on 5 of the 5 benchmarks they both report. Llama Nemotron Super 49B v1.5 shipped 104 days before Kimi K2 Thinking, so benchmark comparisons should account for the intervening progress.

Kimi K2 Thinking has 1T parameters, while Llama Nemotron Super 49B v1.5 has 49B. Context windows are 256k (Kimi K2 Thinking) vs 128k (Llama Nemotron Super 49B v1.5).

On LiveCodeBench, Kimi K2 Thinking leads at 83.1% vs Llama Nemotron Super 49B v1.5 at 73.58%. On Humanity's Last Exam · text only, no tools, Kimi K2 Thinking leads at 23.9% vs Llama Nemotron Super 49B v1.5 at 7.64%. On AIME 2025, Kimi K2 Thinking leads at 94.5% vs Llama Nemotron Super 49B v1.5 at 82.71%. On GPQA Diamond, Kimi K2 Thinking leads at 84.5% vs Llama Nemotron Super 49B v1.5 at 71.97%. On MMLU-Pro, Kimi K2 Thinking leads at 84.6% vs Llama Nemotron Super 49B v1.5 at 79.53%.