Compare AI models

Specifications
Parameters
1T27B
Context window
256k256k
API pricing
Cheapest input
$0.60Novita—
Cheapest output
$2.50Novita—
$245Novita · fp8—
Benchmarks
SWE-Bench Verified
69.2%77.2%
SWE-Bench Multilingual
55.9%71.3%
GPQA Diamond
74.2%87.8%
MMLU-Pro
81.9%86.2%
Overview
CompanyMoonshot AIQwen
Release dateSep 5 2025Apr 22 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.6-27B leads Kimi K2 (0905) on 4 of the 4 benchmarks they both report (SWE-Bench Verified, SWE-Bench Multilingual, GPQA Diamond, MMLU-Pro). Kimi K2 (0905) shipped 229 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.

Kimi K2 (0905) has 1T parameters, while Qwen3.6-27B has 27B. Context windows are 256k (Kimi K2 (0905)) vs 256k (Qwen3.6-27B).

On SWE-Bench Verified, Qwen3.6-27B leads at 77.2% vs Kimi K2 (0905) at 69.2%. On SWE-Bench Multilingual, Qwen3.6-27B leads at 71.3% vs Kimi K2 (0905) at 55.9%. On GPQA Diamond, Qwen3.6-27B leads at 87.8% vs Kimi K2 (0905) at 74.2%. On MMLU-Pro, Qwen3.6-27B leads at 86.2% vs Kimi K2 (0905) at 81.9%.