Skip to main content

Head-to-head comparison

Gemini 3.8 Flash vs. Kimi K2.6

Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.

shared result series
22
distinct benchmarks
22
latest retrieval
2026-09-02

Change model selection

Specifications

General specifications

Release date, availability, context window, architecture, and published parameter counts at a glance. Undisclosed details remain marked as unavailable.

Specifications for Gemini 3.8 Flash and Kimi K2.6
AttributeGemini 3.8 FlashKimi K2.6
ProviderGoogleMoonshot AI
ReleasedSep 2, 2026Apr 20, 2026
AvailabilityActiveActive
Model typeProprietaryOpen Weights
ParametersNot published1T, 32B active
ArchitectureNot publishedMixture of Experts
Context window1,048,576 tokens262,144 tokens
Knowledge cutoffMarch 2026Not published
Technical sourcesModel, Knowledge cutoffModel, Context

Pricing

API pricing compared

The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.

API pricing for Gemini 3.8 Flash and Kimi K2.6
Price typeGemini 3.8 FlashKimi K2.6
API input$0.75$0.95
API output$3.75$4
Cache read$0.07$0.16
Cache write (5 min.)Not listedNot listed
Cache write (1 hr.)Not listedNot listed
Price verified09/02/2026 Source07/30/2026 Source
Gemini 3.8 FlashKimi K2.6
API inputUSD per 1M tokens, base tier
Gemini 3.8 FlashLower price$0.75
Kimi K2.6$0.95
API outputUSD per 1M tokens, base tier
Gemini 3.8 FlashLower price$3.75
Kimi K2.6$4
Cache readUSD per 1M tokens, base tier
Gemini 3.8 FlashLower price$0.075
Kimi K2.6$0.16

Key to the marks:better valuebetter, but not conclusivetie

Pricing by provider

Direct developer pricing and provider endpoint tariffs routed through OpenRouter are listed separately. Prices are in USD per 1M tokens. Context-dependent direct tiers plus regional, Flex, Priority, and other OpenRouter tariffs remain individually identifiable.

Provider pricing for Gemini 3.8 Flash and Kimi K2.6
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
Gemini 3.8 FlashGoogleDirect from developerStandard API$0.75$3.75Source09/02/2026
GoogleVia OpenRoutergoogle-vertex/global$0.75$3.75Source09/02/2026
GoogleVia OpenRoutergoogle-vertex/global/flexLowest listed price: $0.375Lowest listed price: $1.875Source09/02/2026
GoogleVia OpenRoutergoogle-vertex/global/priority$1.35$6.75Source09/02/2026
Google AI StudioVia OpenRoutergoogle-ai-studio$0.75$3.75Source09/02/2026
Google AI StudioVia OpenRoutergoogle-ai-studio/flexLowest listed price: $0.375Lowest listed price: $1.875Source09/02/2026
Google AI StudioVia OpenRoutergoogle-ai-studio/priority$1.35$6.75Source09/02/2026
Kimi K2.6Moonshot AIDirect from developerStandard API$0.95$4Source07/30/2026
AtlasCloudVia OpenRouteratlas-cloud/int4$0.95$4Source09/02/2026
BaiduVia OpenRouterbaidu/fp4Lowest listed price: $0.5292Lowest listed price: $2.228Source09/02/2026
BaseTenVia OpenRouterbaseten/fp4#1$0.95$4Source09/02/2026
BaseTenVia OpenRouterbaseten/fp4#2$0.95$4Source09/02/2026
ChutesVia OpenRouterchutes/int4$0.58$3.4Source09/02/2026
CloudflareVia OpenRoutercloudflare$0.95$4Source09/02/2026
CoreWeaveVia OpenRoutercoreweave/fp4$0.65$3.41Source09/02/2026
CrusoeVia OpenRoutercrusoe/bf16$0.7$3.5Source09/02/2026
DecartVia OpenRouterdecart/fp4$0.5372$2.2618Source09/02/2026
DeepInfraVia OpenRouterdeepinfra/fp4$0.75$3.5Source09/02/2026
DigitalOceanVia OpenRouterdigitalocean$0.95$4Source09/02/2026
FireworksVia OpenRouterfireworks$0.95$4Source09/02/2026
GMICloudVia OpenRoutergmicloud/fp8$0.855$3.6Source09/02/2026
InceptronVia OpenRouterinceptron/int4$0.53$2.5Source09/02/2026
Moonshot AIVia OpenRoutermoonshotai/int4$0.95$4Source09/02/2026
NovitaVia OpenRouternovita$0.8$3.4Source09/02/2026
ParasailVia OpenRouterparasail/int4$0.75$3.5Source09/02/2026
PhalaVia OpenRouterphala$1.09$4.6Source09/02/2026
SiliconFlowVia OpenRoutersiliconflow/fp8$0.77$3.4Source09/02/2026
StreamLakeVia OpenRouterstreamlake/fp8$0.5985$2.52Source09/02/2026
VeniceVia OpenRoutervenice/int4$0.75$3.5Source09/02/2026

Performance

Shared benchmarks

Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.

Capability profile from matched benchmarks

Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.

255075100CodingReasoningKnowledgeFinanceLegalAgentic tasksMultimodalProductivity
Gemini 3.8 Flash
Kimi K2.6
Coding: 100 / 63.3 (5 benchmark families)
Reasoning: 100 / 94.4 (1 benchmark family)
Knowledge: 100 / 97.1 (1 benchmark family)
Finance: 99.8 / 88.3 (4 benchmark families)
Legal: 100 / 51.6 (3 benchmark families)
Agentic tasks: 100 / 65.9 (1 benchmark family)
Multimodal: 100 / 96.9 (1 benchmark family)
Productivity: 100 / 86.7 (1 benchmark family)

22 matched rows from 22 benchmark families were considered. The radar shows 8 of 12 comparable categories.

Gemini 3.8 FlashKimi K2.6
Code MigrationOverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner36.546 %
Kimi K2.627.768 %
CyberBenchOverall. Higher is better. No documented setup difference
Gemini 3.8 Flash43.75 %
Kimi K2.6Winner74.351 %
EMBOverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner72.196 %
Kimi K2.657.855 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner61.435 %
Kimi K2.644.899 %
GPQA DiamondOverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner94.444 %
Kimi K2.689.142 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner10 %
Kimi K2.61.667 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner38.942 %
Kimi K2.615.865 %
LegalBenchOverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner86.993 %
Kimi K2.684.738 %
LiveCodeBench v6Overall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner89.484 %
Kimi K2.686.771 %
MedCodeOverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner48.135 %
Kimi K2.640.142 %
MedScribeOverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner84.496 %
Kimi K2.678.149 %
MMLU-ProOverall. Higher is better. No documented setup difference
Gemini 3.8 FlashWinner90.221 %
Kimi K2.687.572 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Gemini 3.8 Flash and Kimi K2.6
Benchmark and taskGemini 3.8 FlashKimi K2.6Source
Code MigrationOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner36.546 %
27.768 %
Vals AI
Source details
Data as of: 09/01/2026
CyberBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
43.75 %
Winner74.351 %
Vals AI
Source details
Data as of: 09/01/2026
EMBOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner72.196 %
57.855 %
Vals AI
Source details
Data as of: 09/01/2026
Finance Agent (v2)Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better
Winner61.435 %
44.899 %
Vals AI
Source details
Data as of: 09/01/2026
GPQA DiamondOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner94.444 %
89.142 %
Vals AI
Source details
Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved
Test details
No documented difference in the test setupVersion: 1Metric: task resolution rateScoring: Higher is better
Winner10 %
1.667 %
Vals AI
Source details
Data as of: 09/01/2026
Legal Research BenchOverall · All-pass
Test details
No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is better
Winner38.942 %
15.865 %
Vals AI
Source details
Data as of: 09/01/2026
LegalBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner86.993 %
84.738 %
Vals AI
Source details
Data as of: 09/01/2026
LiveCodeBench v6Overall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner89.484 %
86.771 %
Vals AI
Source details
Data as of: 09/01/2026
MedCodeOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner48.135 %
40.142 %
Vals AI
Source details
Data as of: 09/01/2026
MedScribeOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner84.496 %
78.149 %
Vals AI
Source details
Data as of: 09/01/2026
MMLU-ProOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner90.221 %
87.572 %
Vals AI
Source details
Data as of: 09/01/2026
MMMU-ProOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner89.075 %
86.301 %
Vals AI
Source details
Data as of: 09/01/2026
MortgageTaxOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
65.342 %
Winner65.818 %
Vals AI
Source details
Data as of: 09/01/2026
ProgramBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner1 %
0 %
Vals AI
Source details
Data as of: 09/01/2026
Public Benefits Bench v1.1Overall
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is better
Winner65.291 %
56.631 %
Vals AI
Source details
Data as of: 09/01/2026
SAGEOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
35.064 %
Winner50.224 %
Vals AI
Source details
Data as of: 09/01/2026
SWE-bench VerifiedOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner80 %
76.2 %
Vals AI
Source details
Data as of: 09/01/2026
TaxEval v2Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better
74.448 %
Winner74.652 %
Vals AI
Source details
Data as of: 09/01/2026
Terminal-Bench 2.1Overall
Test details
No documented difference in the test setupVersion: 2.1Metric: accuracyScoring: Higher is better
Winner81.273 %
53.558 %
Vals AI
Source details
Data as of: 09/01/2026
Vals IndexOverall
Test details
No documented difference in the test setupVersion: 2Metric: weighted index scoreScoring: Higher is better
Winner62.252 %
43.465 %
Vals AI
Source details
Data as of: 09/01/2026
Vibe Code Bench v1.1Overall
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands
Winner78.651 %
37.891 %
Vals AI
Source details
Data as of: 09/01/2026

Key to the marks:better valuebetter, but not conclusivetie

How to read this comparison

Winning one benchmark is not an overall verdict

Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.

The standard price table uses direct developer rates. The provider comparison labels OpenRouter endpoints, regions, and special tariffs separately.

Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.

More matchups

Related LLM comparisons

Compare Gemini 3.8 Flash and Kimi K2.6 with other leading models using the same data and benchmark logic.

View the complete LLM comparison