Compare AI models

Specifications
Parameters
1T>1T
Context window
128k256k
API pricing
Cheapest input
$0.57Novita—
Cheapest output
$2.30Novita—
$229Novita · fp8—
Benchmarks
SWE-Bench Verified
65.8%75.3%
LiveCodeBench
53.7%85.9%
Humanity's Last Exam · text only, no tools
4.7%30.2%
GPQA Diamond
75.1%87.4%
MMLU-Pro
81.1%85.7%
Overview
CompanyMoonshot AIQwen
Release dateJul 11 2025Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen3-Max-Thinking leads Kimi K2 on 5 of the 5 benchmarks they both report. Kimi K2 shipped 199 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.

Kimi K2 has 1T parameters, while Qwen3-Max-Thinking has >1T. Context windows are 128k (Kimi K2) vs 256k (Qwen3-Max-Thinking). Kimi K2 is open weight, while Qwen3-Max-Thinking is closed.

On SWE-Bench Verified, Qwen3-Max-Thinking leads at 75.3% vs Kimi K2 at 65.8%. On LiveCodeBench, Qwen3-Max-Thinking leads at 85.9% vs Kimi K2 at 53.7%. On Humanity's Last Exam · text only, no tools, Qwen3-Max-Thinking leads at 30.2% vs Kimi K2 at 4.7%. On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs Kimi K2 at 75.1%. On MMLU-Pro, Qwen3-Max-Thinking leads at 85.7% vs Kimi K2 at 81.1%.