Compare AI models

Specifications
Parameters
1T27B/35B/122B
Context window
256k256k
API pricing
Cheapest input
$0.49AtlasCloud—
Cheapest output
$2.50AtlasCloud—
$223AtlasCloud · int4—
Benchmarks
SWE-Bench Verified
76.8%72%
LiveCodeBench
85%78.9%
Terminal-Bench 2.0
50.8%49.4%
BrowseComp
60.6%63.8%
Humanity's Last Exam · no tools
30.1%25.3%
Humanity's Last Exam · with tools
50.2%47.5%
GPQA Diamond
87.6%86.6%
MMLU-Pro
87.1%86.7%
OSWorld-Verified
63.3%58%
Overview
CompanyMoonshot AIQwen
Release dateJan 27 2026Feb 24 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2.5 leads Qwen3.5 Medium on 8 of the 9 benchmarks they both report. Kimi K2.5 shipped 28 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.

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

On SWE-Bench Verified, Kimi K2.5 leads at 76.8% vs Qwen3.5 Medium at 72%. On LiveCodeBench, Kimi K2.5 leads at 85% vs Qwen3.5 Medium at 78.9%. On Terminal-Bench 2.0, Kimi K2.5 leads at 50.8% vs Qwen3.5 Medium at 49.4%. On BrowseComp, Qwen3.5 Medium leads at 63.8% vs Kimi K2.5 at 60.6%. On Humanity's Last Exam · no tools, Kimi K2.5 leads at 30.1% vs Qwen3.5 Medium at 25.3%. On Humanity's Last Exam · with tools, Kimi K2.5 leads at 50.2% vs Qwen3.5 Medium at 47.5%. On GPQA Diamond, Kimi K2.5 leads at 87.6% vs Qwen3.5 Medium at 86.6%. On MMLU-Pro, Kimi K2.5 leads at 87.1% vs Qwen3.5 Medium at 86.7%. On OSWorld-Verified, Kimi K2.5 leads at 63.3% vs Qwen3.5 Medium at 58%.