Skip to main content

Head-to-head comparison

GPT-5.4 mini 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
143
distinct benchmarks
21
latest retrieval
2026-09-04

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 GPT-5.4 mini and Kimi K2.6
AttributeGPT-5.4 miniKimi K2.6
ProviderOpenAIMoonshot AI
ReleasedMar 2026Apr 20, 2026
AvailabilityActiveActive
Model typeProprietaryOpen Weights
ParametersNot published1T, 32B active
ArchitectureNot publishedMixture of Experts
Context window400,000 tokens262,144 tokens
Knowledge cutoffAugust 31, 2025Not published
Technical sourcesModelModel, 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 GPT-5.4 mini and Kimi K2.6
Price typeGPT-5.4 miniKimi K2.6
API input$0.75$0.95
API output$4.5$4
Cache read$0.07$0.16
Cache write (5 min.)Not listedNot listed
Cache write (1 hr.)Not listedNot listed
Price verified07/30/2026 Source07/30/2026 Source
GPT-5.4 miniKimi K2.6
API inputUSD per 1M tokens, base tier
GPT-5.4 miniLower price$0.75
Kimi K2.6$0.95
API outputUSD per 1M tokens, base tier
GPT-5.4 mini$4.5
Kimi K2.6Lower price$4
Cache readUSD per 1M tokens, base tier
GPT-5.4 miniLower 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 GPT-5.4 mini and Kimi K2.6
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
GPT-5.4 miniOpenAIDirect from developerStandard API$0.75$4.5Source07/30/2026
AzureVia OpenRouterazure$0.75$4.5Source09/07/2026
AzureVia OpenRouterazure/us$0.825$4.95Source09/07/2026
OpenAIVia OpenRouteropenai$0.75$4.5Source09/07/2026
OpenAIVia OpenRouteropenai/fast$1.5$9Source09/07/2026
OpenAIVia OpenRouteropenai/flexLowest listed price: $0.375Lowest listed price: $2.25Source09/07/2026
Kimi K2.6Moonshot AIDirect from developerStandard API$0.95$4Source07/30/2026
AtlasCloudVia OpenRouteratlas-cloud/int4$0.95$4Source09/07/2026
BaiduVia OpenRouterbaidu/fp4$0.95$4Source09/07/2026
BaseTenVia OpenRouterbaseten/fp4#1$0.95$4Source09/07/2026
BaseTenVia OpenRouterbaseten/fp4#2$0.95$4Source09/07/2026
ChutesVia OpenRouterchutes/int4$0.58$3.4Source09/07/2026
CloudflareVia OpenRoutercloudflare$0.95$4Source09/07/2026
CoreWeaveVia OpenRoutercoreweave/fp4$0.65$3.41Source09/07/2026
CrusoeVia OpenRoutercrusoe/bf16$0.7$3.5Source09/07/2026
DecartVia OpenRouterdecart/fp4$0.5865Lowest listed price: $2.4696Source09/07/2026
DeepInfraVia OpenRouterdeepinfra/fp4$0.75$3.5Source09/07/2026
DigitalOceanVia OpenRouterdigitalocean$0.95$4Source09/07/2026
FireworksVia OpenRouterfireworks$0.95$4Source09/07/2026
GMICloudVia OpenRoutergmicloud/fp8$0.855$3.6Source09/07/2026
InceptronVia OpenRouterinceptron/int4Lowest listed price: $0.56$3.39Source09/07/2026
Moonshot AIVia OpenRoutermoonshotai/int4$0.95$4Source09/07/2026
NovitaVia OpenRouternovita$0.8$3.4Source09/07/2026
ParasailVia OpenRouterparasail/int4$0.75$3.5Source09/07/2026
PhalaVia OpenRouterphala$1.09$4.6Source09/07/2026
SiliconFlowVia OpenRoutersiliconflow/fp8$0.77$3.4Source09/07/2026
StreamLakeVia OpenRouterstreamlake/fp8$0.5985$2.52Source09/07/2026
VeniceVia OpenRoutervenice/int4$0.75$3.5Source09/07/2026

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 tasksMultimodalEducation
GPT-5.4 mini
Kimi K2.6
Coding: 87.3 / 95.8 (5 benchmark families)
Reasoning: 93.2 / 100 (1 benchmark family)
Knowledge: 96.6 / 100 (1 benchmark family)
Finance: 92.3 / 99.8 (5 benchmark families)
Legal: 39.4 / 100 (2 benchmark families)
Agentic tasks: 89.2 / 99 (1 benchmark family)
Multimodal: 91.8 / 100 (1 benchmark family)
Education: 100 / 98.8 (1 benchmark family)

22 matched rows from 19 benchmark families were considered. The radar shows 8 of 9 comparable categories.

GPT-5.4 miniKimi K2.6
Code MigrationOverall. Higher is better. No documented setup difference
GPT-5.4 mini12.936 %
Kimi K2.6Winner27.768 %
CorpFin v2Overall. Higher is better. No documented setup difference
GPT-5.4 mini60.917 %
Kimi K2.6Winner66.744 %
EMBOverall. Higher is better. No documented setup difference
GPT-5.4 mini45.426 %
Kimi K2.6Winner57.855 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
GPT-5.4 miniWinner45.36 %
Kimi K2.644.899 %
GPQA DiamondOverall. Higher is better. No documented setup difference
GPT-5.4 mini83.08 %
Kimi K2.6Winner89.142 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
GPT-5.4 mini0 %
Kimi K2.6Winner1.667 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
GPT-5.4 mini12.5 %
Kimi K2.6Winner15.865 %
LiveCodeBench v6Overall. Higher is better. No documented setup difference
GPT-5.4 mini81.465 %
Kimi K2.6Winner86.771 %
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
GPT-5.4 mini1,448.118
Kimi K2.6Higher measured value1,460.613
MMLU-ProOverall. Higher is better. No documented setup difference
GPT-5.4 mini84.554 %
Kimi K2.6Winner87.572 %
MMMU-ProOverall. Higher is better. No documented setup difference
GPT-5.4 mini79.249 %
Kimi K2.6Winner86.301 %
MortgageTaxOverall. Higher is better. No documented setup difference
GPT-5.4 mini63.514 %
Kimi K2.6Winner65.818 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for GPT-5.4 mini and Kimi K2.6
Benchmark and taskGPT-5.4 miniKimi K2.6Source
Code MigrationOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
12.936 %
Winner27.768 %
Vals AI
Source details
Data as of: 09/03/2026
CorpFin v2Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
60.917 %
Winner66.744 %
Vals AI
Source details
Data as of: 08/12/2026
EMBOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
45.426 %
Winner57.855 %
Vals AI
Source details
Data as of: 09/03/2026
Finance Agent (v2)Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
Winner45.36 %
44.899 %
Vals AI
Source details
Data as of: 09/03/2026
GPQA DiamondOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
83.08 %
Winner89.142 %
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 betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
0 %
Winner1.667 %
Vals AI
Source details
Data as of: 09/03/2026
Legal Research BenchOverall · All-pass
Test details
No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
12.5 %
Winner15.865 %
Vals AI
Source details
Data as of: 09/03/2026
LiveCodeBench v6Overall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
81.465 %
Winner86.771 %
Vals AI
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlOverall
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena text, style control
Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 59,472 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 37,573 anonymous pairwise votes.
1,448.118
95% confidence interval: ±3.851The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Higher measured value1,460.613
95% confidence interval: ±4.534The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.		LMArena
Source details
Data as of: 09/01/2026
MMLU-ProOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
84.554 %
Winner87.572 %
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 betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
79.249 %
Winner86.301 %
Vals AI
Source details
Data as of: 09/01/2026
MortgageTaxOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
63.514 %
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 betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
Tie0 %
Tie0 %
Vals AI
Source details
Data as of: 09/01/2026
SAGEOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
Winner50.813 %
50.224 %
Vals AI
Source details
Data as of: 09/03/2026
SWE-bench VerifiedOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
73 %
Winner76.2 %
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 betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
71.218 %
Winner74.652 %
Vals AI
Source details
Data as of: 09/01/2026
Terminal-Bench 2.0Overall
Test details
No documented difference in the test setupVersion: 2.0Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
44.944 %
Winner57.303 %
Vals AI
Source details
Data as of: 06/04/2026
Terminal-Bench 2.1Overall
Test details
No documented difference in the test setupVersion: 2.1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
Winner54.682 %
53.558 %
Vals AI
Source details
Data as of: 09/03/2026
Vals IndexOverall
Test details
No documented difference in the test setupVersion: 2Metric: weighted index scoreScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
39.632 %
Winner43.465 %
Vals AI
Source details
Data as of: 09/03/2026
Vals Multimodal IndexOverall
Test details
No documented difference in the test setupVersion: 1.2Metric: weighted index scoreScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17
54.219 %
Winner56.434 %
Vals AI
Source details
Data as of: 08/11/2026
Vibe Code Bench v1.1Overall
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Harness: OpenHands
Kimi K2.6: Harness: OpenHands
Winner47.969 %
37.891 %
Vals AI
Source details
Data as of: 09/03/2026
Code MigrationCLI
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
8.2 %
Higher measured value17.977 %
Vals AI
Source details
Data as of: 08/09/2026
CorpFin v2Exact Pages
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 48,000 tokens
61.538 %
Higher measured value64.802 %
Vals AI
Source details
Data as of: 08/06/2026
EMBComps
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
40.488 %
Higher measured value61.395 %
Vals AI
Source details
Data as of: 08/06/2026
Finance Agent (v2)Adjustments
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
Higher measured value45.366 %
37.934 %
Vals AI
Source details
Data as of: 08/06/2026
GPQA DiamondFew-Shot CoT
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
84.848 %
Higher measured value89.899 %
Vals AI
Source details
Data as of: 08/09/2026
Legal Research BenchAdministrative / Regulatory · All-pass
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
15.152 %
Higher measured value18.182 %
Vals AI
Source details
Data as of: 08/06/2026
LiveCodeBench v6Easy
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 256,000 tokens
97.826 %
Higher measured value99.068 %
Vals AI
Source details
Data as of: 08/09/2026
LMArena Text, Style ControlBusiness, management and finance
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena text, style control
Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 12,113 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 7,489 anonymous pairwise votes.
Higher measured value1,459.508
95% confidence interval: ±6.653The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,455.777
95% confidence interval: ±7.725The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.		LMArena
Source details
Data as of: 09/01/2026
MMLU-ProBiology
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 96,000 tokens
91.353 %
Higher measured value93.724 %
Vals AI
Source details
Data as of: 08/09/2026
MortgageTaxNumerical Extraction
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
Higher measured value79.412 %
74.483 %
Vals AI
Source details
Data as of: 08/09/2026
ProgramBenchAlmost Resolved
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
Higher measured value3 %
0.5 %
Vals AI
Source details
Data as of: 08/09/2026
SAGEAutomata
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 30,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 96,000 tokens
41.27 %
Higher measured value42.857 %
Vals AI
Source details
Data as of: 08/09/2026
SWE-bench Verified<15 min fix
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
85.567 %
Higher measured value87.629 %
Vals AI
Source details
Data as of: 08/08/2026
TaxEval v2Correctness
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
Higher measured value63.042 %
62.715 %
Vals AI
Source details
Data as of: 08/09/2026
Terminal-Bench 2.0Easy
Test details
Test setup not documented as identicalNo direct winnerVersion: 2.0Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: high, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 256,000 tokens
No direct winner75 %
No direct winner75 %
Vals AI
Source details
Data as of: 06/04/2026
Terminal-Bench 2.1Easy
Test details
Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: high, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 256,000 tokens
75 %
Higher measured value83.333 %
Vals AI
Source details
Data as of: 08/06/2026
Vals IndexCorpFin v2
Test details
Test setup not documented as identicalNo direct winnerVersion: 1.2Metric: benchmark scoreScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
60.256 %
Higher measured value68.182 %
Vals AI
Source details
Data as of: 08/09/2026
Vals Multimodal IndexCorpFin v2
Test details
Test setup not documented as identicalNo direct winnerVersion: 1.2Metric: benchmark scoreScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
60.256 %
Higher measured value68.182 %
Vals AI
Source details
Data as of: 08/09/2026
Code MigrationCOBOL
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
27.143 %
Higher measured value57.143 %
Vals AI
Source details
Data as of: 08/09/2026
CorpFin v2Max Fitting Context
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 48,000 tokens
60.956 %
Higher measured value67.249 %
Vals AI
Source details
Data as of: 08/06/2026
EMBDataroom
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
48.286 %
Higher measured value75.069 %
Vals AI
Source details
Data as of: 08/06/2026
Finance Agent (v2)All-Pass
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
32.369 %
Higher measured value32.584 %
Vals AI
Source details
Data as of: 08/06/2026
GPQA DiamondZero-Shot CoT
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
81.313 %
Higher measured value88.384 %
Vals AI
Source details
Data as of: 08/09/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
69.72 %
Higher measured value75.531 %
Vals AI
Source details
Data as of: 08/06/2026
LiveCodeBench v6Hard
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 256,000 tokens
61.714 %
Higher measured value71.429 %
Vals AI
Source details
Data as of: 08/09/2026
LMArena Text, Style ControlChinese
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena text, style control
Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 3,298 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 1,900 anonymous pairwise votes.
1,477.451
95% confidence interval: ±11.125The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Higher measured value1,526.043
95% confidence interval: ±14.272The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.		LMArena
Source details
Data as of: 09/01/2026
MMLU-ProBusiness
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 96,000 tokens
89.734 %
Higher measured value91.635 %
Vals AI
Source details
Data as of: 08/09/2026
MortgageTaxSemantic Extraction
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
47.615 %
Higher measured value57.154 %
Vals AI
Source details
Data as of: 08/09/2026
ProgramBenchFully Resolved
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
No direct winner0 %
No direct winner0 %
Vals AI
Source details
Data as of: 08/09/2026
SAGECalculus
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 30,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 96,000 tokens
Higher measured value59.259 %
22.839 %
Vals AI
Source details
Data as of: 08/09/2026
SWE-bench Verified>4 hours
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
No direct winner0 %
No direct winner0 %
Vals AI
Source details
Data as of: 08/08/2026
TaxEval v2Stepwise Reasoning
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
79.395 %
Higher measured value86.59 %
Vals AI
Source details
Data as of: 08/09/2026
Terminal-Bench 2.0Hard
Test details
Test setup not documented as identicalNo direct winnerVersion: 2.0Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: high, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 256,000 tokens
24.444 %
Higher measured value36.667 %
Vals AI
Source details
Data as of: 06/04/2026
Terminal-Bench 2.1Hard
Test details
Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: high, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 256,000 tokens
Higher measured value34.444 %
25.556 %
Vals AI
Source details
Data as of: 08/06/2026
Vals IndexFinance Agent v2
Test details
Test setup not documented as identicalNo direct winnerVersion: 1.2Metric: benchmark scoreScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
Higher measured value45.407 %
44.932 %
Vals AI
Source details
Data as of: 08/09/2026
Vals Multimodal IndexFinance Agent v2
Test details
Test setup not documented as identicalNo direct winnerVersion: 1.2Metric: benchmark scoreScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
Higher measured value45.407 %
44.932 %
Vals AI
Source details
Data as of: 08/09/2026
Code MigrationCode Quality
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: mean reviewer code-quality ratingScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
3.053 / 5
Higher measured value3.149 / 5
Vals AI
Source details
Data as of: 08/09/2026
CorpFin v2Shared Max Context
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 48,000 tokens
60.256 %
Higher measured value68.182 %
Vals AI
Source details
Data as of: 08/06/2026
EMBDCF
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
40.605 %
Higher measured value49.675 %
Vals AI
Source details
Data as of: 08/06/2026
Finance Agent (v2)Comparables
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
40.273 %
Higher measured value41.069 %
Vals AI
Source details
Data as of: 08/06/2026
Legal Research BenchBusiness & Commercial · All-pass
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 128,000 tokens
11.628 %
Higher measured value20.93 %
Vals AI
Source details
Data as of: 08/06/2026
LiveCodeBench v6Medium
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-2026-03-17, Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K2.6: Top P: 0.95, Output limit: 256,000 tokens
84.856 %
Higher measured value89.817 %
Vals AI
Source details
Data as of: 08/09/2026
LMArena Text, Style ControlCoding
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4 mini: Snapshot: gpt-5.4-mini-high, Reasoning: high, Harness: Arena text, style control
Kimi K2.6: Snapshot: kimi-k2.6, Harness: Arena text, style controlGPT-5.4 mini: Style-controlled Arena rating from 16,204 anonymous pairwise votes.Kimi K2.6: Style-controlled Arena rating from 10,419 anonymous pairwise votes.
1,495.819
95% confidence interval: ±6.028The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Higher measured value1,514.216
95% confidence interval: ±7.05The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.		LMArena
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 GPT-5.4 mini and Kimi K2.6 with other leading models using the same data and benchmark logic.

View the complete LLM comparison