Compare AI models

Specifications
Parameters
1T>1T
Context window
256k256k
API pricing
Cheapest input
$0.60Novita—
Cheapest output
$2.50Novita—
$245Novita · bf16—
Benchmarks
SWE-Bench Verified
71.3%75.3%
LiveCodeBench
83.1%85.9%
Humanity's Last Exam · text only, no tools
23.9%30.2%
GPQA Diamond
84.5%87.4%
MMLU-Pro
84.6%85.7%
Overview
CompanyMoonshot AIQwen
Release dateNov 6 2025Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen3-Max-Thinking leads Kimi K2 Thinking on 5 of the 5 benchmarks they both report. Kimi K2 Thinking shipped 81 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.

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

On SWE-Bench Verified, Qwen3-Max-Thinking leads at 75.3% vs Kimi K2 Thinking at 71.3%. On LiveCodeBench, Qwen3-Max-Thinking leads at 85.9% vs Kimi K2 Thinking at 83.1%. On Humanity's Last Exam · text only, no tools, Qwen3-Max-Thinking leads at 30.2% vs Kimi K2 Thinking at 23.9%. On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs Kimi K2 Thinking at 84.5%. On MMLU-Pro, Qwen3-Max-Thinking leads at 85.7% vs Kimi K2 Thinking at 84.6%.