Compare AI models

Specifications
Parameters
1T27B/35B/122B
Context window
256k256k
API pricing
Cheapest input
$0.60Novita—
Cheapest output
$2.50Novita—
$245Novita · bf16—
Benchmarks
SWE-Bench Verified
71.3%72%
LiveCodeBench
83.1%78.9%
BrowseComp
60.2%63.8%
GPQA Diamond
84.5%86.6%
MMLU-Pro
84.6%86.7%
Overview
CompanyMoonshot AIQwen
Release dateNov 6 2025Feb 24 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.5 Medium leads Kimi K2 Thinking on 4 of the 5 benchmarks they both report. Kimi K2 Thinking shipped 110 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.

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

On SWE-Bench Verified, Qwen3.5 Medium leads at 72% vs Kimi K2 Thinking at 71.3%. On LiveCodeBench, Kimi K2 Thinking leads at 83.1% vs Qwen3.5 Medium at 78.9%. On BrowseComp, Qwen3.5 Medium leads at 63.8% vs Kimi K2 Thinking at 60.2%. On GPQA Diamond, Qwen3.5 Medium leads at 86.6% vs Kimi K2 Thinking at 84.5%. On MMLU-Pro, Qwen3.5 Medium leads at 86.7% vs Kimi K2 Thinking at 84.6%.