Compare AI models

Specifications
Parameters
1T0.8B/2B/4B/9B
Context window
256k256k
API pricing
Cheapest input
$0.60Novita—
Cheapest output
$2.50Novita—
$245Novita · bf16—
Benchmarks
LiveCodeBench
83.1%65.6%
GPQA Diamond
84.5%81.7%
MMLU-Pro
84.6%82.5%
Overview
CompanyMoonshot AIQwen
Release dateNov 6 2025Mar 2 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2 Thinking leads Qwen3.5 Small on 3 of the 3 benchmarks they both report (LiveCodeBench, GPQA Diamond, MMLU-Pro). Kimi K2 Thinking shipped 116 days before Qwen3.5 Small, so benchmark comparisons should account for the intervening progress.

Kimi K2 Thinking has 1T parameters, while Qwen3.5 Small has 0.8B/2B/4B/9B. Context windows are 256k (Kimi K2 Thinking) vs 256k (Qwen3.5 Small).

On LiveCodeBench, Kimi K2 Thinking leads at 83.1% vs Qwen3.5 Small at 65.6%. On GPQA Diamond, Kimi K2 Thinking leads at 84.5% vs Qwen3.5 Small at 81.7%. On MMLU-Pro, Kimi K2 Thinking leads at 84.6% vs Qwen3.5 Small at 82.5%.