Compare AI models

Specifications
Parameters
1T27B
Context window
256k256k
API pricing
Cheapest input
$0.60Novita—
Cheapest output
$2.50Novita—
$245Novita · bf16—
Benchmarks
SWE-Bench Verified
71.3%77.2%
SWE-Bench Multilingual
61.1%71.3%
LiveCodeBench
83.1%83.9%
GPQA Diamond
84.5%87.8%
MMLU-Pro
84.6%86.2%
Overview
CompanyMoonshot AIQwen
Release dateNov 6 2025Apr 22 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.6-27B leads Kimi K2 Thinking on 5 of the 5 benchmarks they both report. Kimi K2 Thinking shipped 167 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.

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

On SWE-Bench Verified, Qwen3.6-27B leads at 77.2% vs Kimi K2 Thinking at 71.3%. On SWE-Bench Multilingual, Qwen3.6-27B leads at 71.3% vs Kimi K2 Thinking at 61.1%. On LiveCodeBench, Qwen3.6-27B leads at 83.9% vs Kimi K2 Thinking at 83.1%. On GPQA Diamond, Qwen3.6-27B leads at 87.8% vs Kimi K2 Thinking at 84.5%. On MMLU-Pro, Qwen3.6-27B leads at 86.2% vs Kimi K2 Thinking at 84.6%.