Compare AI models

Specifications
Parameters
1T27B/35B/122B
Context window
128k256k
API pricing
Cheapest input
$0.57Novita—
Cheapest output
$2.30Novita—
$229Novita · fp8—
Benchmarks
SWE-Bench Verified
65.8%72%
LiveCodeBench
53.7%78.9%
IFEval
89.8%93.4%
GPQA Diamond
75.1%86.6%
MMLU-Pro
81.1%86.7%
Overview
CompanyMoonshot AIQwen
Release dateJul 11 2025Feb 24 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.5 Medium leads Kimi K2 on 5 of the 5 benchmarks they both report. Kimi K2 shipped 228 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.

Kimi K2 has 1T parameters, while Qwen3.5 Medium has 27B/35B/122B. Context windows are 128k (Kimi K2) vs 256k (Qwen3.5 Medium).

On SWE-Bench Verified, Qwen3.5 Medium leads at 72% vs Kimi K2 at 65.8%. On LiveCodeBench, Qwen3.5 Medium leads at 78.9% vs Kimi K2 at 53.7%. On IFEval, Qwen3.5 Medium leads at 93.4% vs Kimi K2 at 89.8%. On GPQA Diamond, Qwen3.5 Medium leads at 86.6% vs Kimi K2 at 75.1%. On MMLU-Pro, Qwen3.5 Medium leads at 86.7% vs Kimi K2 at 81.1%.