Compare AI models

Specifications
Parameters
1T4B/30B/235B
Context window
256k256k
API pricing
Cheapest input
$0.60Novita—
Cheapest output
$2.50Novita—
$245Novita · bf16—
Benchmarks
LiveCodeBench
83.1%74.1%
Humanity's Last Exam · text only, no tools
23.9%18.2%
AIME 2025
94.5%92.3%
GPQA Diamond
84.5%81.1%
MMLU-Pro
84.6%84.4%
Overview
CompanyMoonshot AIQwen
Release dateNov 6 2025Jul 21 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2 Thinking leads Qwen3-2507 on 5 of the 5 benchmarks they both report. Qwen3-2507 shipped 108 days before Kimi K2 Thinking, so benchmark comparisons should account for the intervening progress.

Kimi K2 Thinking has 1T parameters, while Qwen3-2507 has 4B/30B/235B. Context windows are 256k (Kimi K2 Thinking) vs 256k (Qwen3-2507).

On LiveCodeBench, Kimi K2 Thinking leads at 83.1% vs Qwen3-2507 at 74.1%. On Humanity's Last Exam · text only, no tools, Kimi K2 Thinking leads at 23.9% vs Qwen3-2507 at 18.2%. On AIME 2025, Kimi K2 Thinking leads at 94.5% vs Qwen3-2507 at 92.3%. On GPQA Diamond, Kimi K2 Thinking leads at 84.5% vs Qwen3-2507 at 81.1%. On MMLU-Pro, Kimi K2 Thinking leads at 84.6% vs Qwen3-2507 at 84.4%.