Compare AI models

Specifications
Parameters
1T27B
Context window
256k256k
API pricing
Input price
$0.95—
Output price
$4.00—
Cached input price
$0.16—
Cheapest input
$0.3895Baidu—
Cheapest output
$1.64Baidu—
$160Baidu · fp4—
Benchmarks
SWE-Bench Verified
80.2%77.2%
SWE-Bench Multilingual
76.7%71.3%
LiveCodeBench
89.6%83.9%
Terminal-Bench 2.0
66.7%59.3%
Humanity's Last Exam · no tools
34.7%24%
AIME 2026
96.4%94.1%
GPQA Diamond
90.5%87.8%
Overview
CompanyMoonshot AIQwen
Release dateApr 20 2026Apr 22 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2.6 leads Qwen3.6-27B on 7 of the 7 benchmarks they both report. Only Kimi K2.6 has a verified first-party price for an available API: $0.95 per million input tokens and $4.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.6-27B. Kimi K2.6 shipped 2 days before Qwen3.6-27B, so benchmark comparisons should account for the intervening progress.

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

On SWE-Bench Verified, Kimi K2.6 leads at 80.2% vs Qwen3.6-27B at 77.2%. On SWE-Bench Multilingual, Kimi K2.6 leads at 76.7% vs Qwen3.6-27B at 71.3%. On LiveCodeBench, Kimi K2.6 leads at 89.6% vs Qwen3.6-27B at 83.9%. On Terminal-Bench 2.0, Kimi K2.6 leads at 66.7% vs Qwen3.6-27B at 59.3%. On Humanity's Last Exam · no tools, Kimi K2.6 leads at 34.7% vs Qwen3.6-27B at 24%. On AIME 2026, Kimi K2.6 leads at 96.4% vs Qwen3.6-27B at 94.1%. On GPQA Diamond, Kimi K2.6 leads at 90.5% vs Qwen3.6-27B at 87.8%.