Compare AI models

Specifications
Parameters
1T4B/30B/235B
Context window
128k256k
API pricing
Cheapest input
$0.57Novita—
Cheapest output
$2.30Novita—
$229Novita · fp8—
Benchmarks
LiveCodeBench
53.7%74.1%
IFEval
89.8%87.8%
Humanity's Last Exam · text only, no tools
4.7%18.2%
GPQA Diamond
75.1%81.1%
MMLU-Pro
81.1%84.4%
Overview
CompanyMoonshot AIQwen
Release dateJul 11 2025Jul 21 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3-2507 leads Kimi K2 on 4 of the 5 benchmarks they both report. Kimi K2 shipped 10 days before Qwen3-2507, so benchmark comparisons should account for the intervening progress.

Kimi K2 has 1T parameters, while Qwen3-2507 has 4B/30B/235B. Context windows are 128k (Kimi K2) vs 256k (Qwen3-2507).

On LiveCodeBench, Qwen3-2507 leads at 74.1% vs Kimi K2 at 53.7%. On IFEval, Kimi K2 leads at 89.8% vs Qwen3-2507 at 87.8%. On Humanity's Last Exam · text only, no tools, Qwen3-2507 leads at 18.2% vs Kimi K2 at 4.7%. On GPQA Diamond, Qwen3-2507 leads at 81.1% vs Kimi K2 at 75.1%. On MMLU-Pro, Qwen3-2507 leads at 84.4% vs Kimi K2 at 81.1%.