Kimi K2.6vsGrok 4.6

Kimi K2.6
Grok 4.6
Specifications
Parameters
1T
Context window
256k
API pricing
Input price
$0.95$2.00
Output price
$4.00$6.00
Cached input price
$0.16$0.50
Cheapest input
$0.5367Baidu$2.20Amazon Bedrock
Cheapest output
$2.26Baidu$6.60Amazon Bedrock
Benchmarks
BullshitBench v2
65%65%
Next.js Evals
62%85%
Benchmarks
SWE-Bench Verified
80.2%
DeepSWE 1.1
65.9%
FrontierCode v1.1 (Extended) · extended split
61.3%
APEX-SWE
56.4%
LiveCodeBench
89.6%
Terminal-Bench 4.0
20.3%
Terminal-Bench 3.0
26%
APEX-Agents
57.5%
BrowseComp
83.2%
Humanity's Last Exam · with tools
34.7%
GPQA Diamond
90.5%
OSWorld-Verified
73.1%
Harvey's Legal Agent Benchmark
15.8%
AA Intelligence Index
61
GDPval-AA v2
1753
AA-Briefcase
1577
Overview
CompanyMoonshot AISpaceXAI
Release dateApr 21 2026Aug 12 2026
AccessOpen WeightProprietary

Other comparisons

Kimi K2.6vsClaude Fable 5.1Grok 4.6vsClaude Fable 5.1Kimi K2.6vsGPT-6 AstraGrok 4.6vsGPT-6 AstraKimi K2.6vsGemini 3.8 FlashGrok 4.6vsGemini 3.8 FlashKimi K2.6vsMuse Spark 1.3Grok 4.6vsMuse Spark 1.3Kimi K2.6vsDeepSeek-V4-Pro-0813Grok 4.6vsDeepSeek-V4-Pro-0813Kimi K2.6vsMistral Medium 3.5Grok 4.6vsMistral Medium 3.5

Frequently asked questions

Grok 4.6 leads Kimi K2.6 on 1 of the 2 benchmarks they both report (BullshitBench v2, Next.js Evals). Kimi K2.6 is cheaper on both input and output: $0.95 vs $2.00 per million input tokens, and $4.00 vs $6.00 per million output tokens. Figures are base-tier rates. Kimi K2.6 shipped 113 days before Grok 4.6, so benchmark comparisons should account for the intervening progress.

Kimi K2.6 is open weight, while Grok 4.6 is proprietary.

On BullshitBench v2, both models score 65%. On Next.js Evals, Grok 4.6 leads at 85% vs Kimi K2.6 at 62%.