Kimi K2.5vsGrok 4.6

Kimi K2.5
Grok 4.6
Specifications
Parameters
1T
Context window
256k
API pricing
Input price
$0.60$2.00
Output price
$3.00$6.00
Cached input price
$0.10$0.50
Cheapest input
$0.45SiliconFlow$2.20Amazon Bedrock
Cheapest output
$2.25SiliconFlow$6.60Amazon Bedrock
Benchmarks
BullshitBench v2
52%66%
Next.js Evals
16%71%
Benchmarks
SWE-Bench Verified
76.8%
DeepSWE 1.1
65.9%
FrontierCode v1.1 (Extended) · extended split
61.3%
APEX-SWE
56.4%
LiveCodeBench
85%
Terminal-Bench 4.0
20.3%
Terminal-Bench 3.0
26%
APEX-Agents
57.5%
BrowseComp
60.6%
Humanity's Last Exam · with tools
30.1%
GPQA Diamond
87.6%
Harvey's Legal Agent Benchmark
15.8%
AA Intelligence Index
61
GDPval-AA v2
1753
AA-Briefcase
1577
threejseval
1519
Overview
CompanyMoonshot AISpaceXAI
Release dateJan 27 2026Aug 12 2026
AccessOpen WeightProprietary

Other comparisons

Kimi K2.5vsClaude Fable 5.1Grok 4.6vsClaude Fable 5.1Kimi K2.5vsGPT-6 AstraGrok 4.6vsGPT-6 AstraKimi K2.5vsGemini 3.8 FlashGrok 4.6vsGemini 3.8 FlashKimi K2.5vsMuse Spark 1.3Grok 4.6vsMuse Spark 1.3Kimi K2.5vsDeepSeek-V4.1-FlashGrok 4.6vsDeepSeek-V4.1-FlashKimi K2.5vsMistral Medium 3.5Grok 4.6vsMistral Medium 3.5

Frequently asked questions

Grok 4.6 leads Kimi K2.5 on 2 of the 2 benchmarks they both report (BullshitBench v2, Next.js Evals). Kimi K2.5 is cheaper on both input and output: $0.60 vs $2.00 per million input tokens, and $3.00 vs $6.00 per million output tokens. Figures are base-tier rates. Kimi K2.5 shipped 197 days before Grok 4.6, so benchmark comparisons should account for the intervening progress.

Kimi K2.5 is open weight, while Grok 4.6 is proprietary.

On BullshitBench v2, Grok 4.6 leads at 66% vs Kimi K2.5 at 52%. On Next.js Evals, Grok 4.6 leads at 71% vs Kimi K2.5 at 16%.