Gemini 3.6 FlashvsKimi K2.6

Gemini 3.6 Flash
Kimi K2.6
Specifications
Parameters
1T
Context window
256k
API pricing
Input price
$0.75$0.95
Output price
$3.75$4.00
Cached input price
$0.075$0.16
Cheapest input
$0.5795Baidu
Cheapest output
$2.44Baidu
Benchmarks
BullshitBench v2
39%65%
OSWorld-Verified
83%73.1%
Benchmarks
Gray Swan IPI · k = 1
7.3%
Gray Swan IPI · k = 10
32.2%
Gray Swan IPI · k = 15
37.3%
ProgramBench
0.5%
SWE-Bench Verified
80.2%
DeepSWE 1.1
49%
MLE-Bench
63.9%
Next.js Evals
52%
LiveCodeBench
89.6%
BU Bench
68%
BrowseComp
83.2%
Humanity's Last Exam · with tools
34.7%
GPQA Diamond
90.5%
GDPval-AA v2
1421
threejseval
1406
Overview
CompanyGoogleMoonshot AI
Release dateJul 21 2026Apr 21 2026
AccessProprietaryOpen Weight

Other comparisons

Gemini 3.6 FlashvsClaude Fable 5.1Kimi K2.6vsClaude Fable 5.1Gemini 3.6 FlashvsGPT-6 AstraKimi K2.6vsGPT-6 AstraGemini 3.6 FlashvsMuse Spark 1.3Kimi K2.6vsMuse Spark 1.3Gemini 3.6 FlashvsGrok 4.6Kimi K2.6vsGrok 4.6Gemini 3.6 FlashvsDeepSeek-V4.1-FlashKimi K2.6vsDeepSeek-V4.1-FlashGemini 3.6 FlashvsMistral Medium 3.5Kimi K2.6vsMistral Medium 3.5

Frequently asked questions

Gemini 3.6 Flash and Kimi K2.6 are evenly matched across the 2 benchmarks they both report (BullshitBench v2, OSWorld-Verified). Gemini 3.6 Flash is cheaper on both input and output: $0.75 vs $0.95 per million input tokens, and $3.75 vs $4.00 per million output tokens. Kimi K2.6 shipped 91 days before Gemini 3.6 Flash, so benchmark comparisons should account for the intervening progress.

Gemini 3.6 Flash is proprietary, while Kimi K2.6 is open weight.

On BullshitBench v2, Kimi K2.6 leads at 65% vs Gemini 3.6 Flash at 39%. On OSWorld-Verified, Gemini 3.6 Flash leads at 83% vs Kimi K2.6 at 73.1%.