DeepSeek-V4-ProvsKimi K2 (0905)

DeepSeek-V4-Pro
Kimi K2 (0905)
Specifications
Parameters
1T
Context window
256k
API pricing
Cheapest input
$0.7078StreamLake$0.60Novita
Cheapest output
$1.4157StreamLake$2.50Novita
Benchmarks
GPQA Diamond
90.1%75.1%
Benchmarks
BullshitBench v2
14%
SWE-Bench Verified
65.8%
LiveCodeBench
93.5%
BrowseComp
83.4%
Overview
CompanyDeepSeekMoonshot AI
Release dateApr 24 2026Sep 5 2025
AccessOpen WeightOpen Weight

Other comparisons

DeepSeek-V4-ProvsClaude Fable 5.1Kimi K2 (0905)vsClaude Fable 5.1DeepSeek-V4-ProvsGPT-6 AstraKimi K2 (0905)vsGPT-6 AstraDeepSeek-V4-ProvsGemini 3.8 FlashKimi K2 (0905)vsGemini 3.8 FlashDeepSeek-V4-ProvsMuse Spark 1.3Kimi K2 (0905)vsMuse Spark 1.3DeepSeek-V4-ProvsGrok 4.6Kimi K2 (0905)vsGrok 4.6DeepSeek-V4-ProvsMistral Medium 3.5Kimi K2 (0905)vsMistral Medium 3.5

Frequently asked questions

DeepSeek-V4-Pro leads Kimi K2 (0905) on 1 of the 1 benchmark they both report (GPQA Diamond). Kimi K2 (0905) shipped 231 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On GPQA Diamond, DeepSeek-V4-Pro leads at 90.1% vs Kimi K2 (0905) at 75.1%.