Skip to main content

Head-to-head comparison

GPT-5.5 vs. Kimi K3

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

shared result series
229
distinct benchmarks
27
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-5.5 and Kimi K3
AttributeGPT-5.5Kimi K3
ProviderOpenAIMoonshot AI
ReleasedApr 23, 2026Jul 16, 2026
AvailabilityActiveActive
Model typeProprietaryOpen Weights
ParametersNot published2.8T, 104B active
ArchitectureNot publishedMixture of Experts
Context window1,050,000 tokens1,048,576 tokens
Knowledge cutoffDecember 1, 2025Not published
Technical sourcesModelModel

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-5.5 and Kimi K3
Price typeGPT-5.5Kimi K3
API input$5 ≤272K / $10 >272K$3
API output$30 ≤272K / $45 >272K$15
Cache read$0.5 ≤272K / $1 >272K$0.3
Cache write (5 min.)Not listedNot listed
Cache write (1 hr.)Not listedNot listed
Price verified07/30/2026 Source07/30/2026 Source
GPT-5.5Kimi K3
API inputUSD per 1M tokens, base tier
GPT-5.5$5
Kimi K3Lower price$3
API outputUSD per 1M tokens, base tier
GPT-5.5$30
Kimi K3Lower price$15
Cache readUSD per 1M tokens, base tier
GPT-5.5$0.5
Kimi K3Lower price$0.3

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-5.5 and Kimi K3
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
GPT-5.5OpenAIDirect from developerUp to 272,000 context tokens$5$30Source07/30/2026
OpenAIDirect from developerAbove 272,000 context tokens$10$45Source07/30/2026
Amazon BedrockVia OpenRouteramazon-bedrock/us-east-1$5.5$33Source09/08/2026
AzureVia OpenRouterazure$5$30Source09/08/2026
AzureVia OpenRouterazure/eu$5.5$33Source09/08/2026
AzureVia OpenRouterazure/us$5.5$33Source09/08/2026
OpenAIVia OpenRouteropenai$5$30Source09/08/2026
OpenAIVia OpenRouteropenai/fast$12.5$75Source09/08/2026
OpenAIVia OpenRouteropenai/flexLowest listed price: $2.5Lowest listed price: $15Source09/08/2026
Kimi K3Moonshot AIDirect from developerStandard API$3$15Source07/30/2026
AlibabaVia OpenRouteralibaba$3.45$17.25Source09/08/2026
BaseTenVia OpenRouterbaseten/fp8$3$15Source09/08/2026
ChutesVia OpenRouterchutes/mxfp4$3$15Source09/08/2026
DeepInfraVia OpenRouterdeepinfra/bf16$2.85$14.25Source09/08/2026
DigitalOceanVia OpenRouterdigitalocean$2.85$14.25Source09/08/2026
FireworksVia OpenRouterfireworks$3$15Source09/08/2026
FireworksVia OpenRouterfireworks/fast$4.5$22.5Source09/08/2026
FireworksVia OpenRouterfireworks/us$3.3$16.5Source09/08/2026
MakoraVia OpenRoutermakora$2.55Lowest listed price: $12.75Source09/08/2026
ModalVia OpenRoutermodal/mxfp4$3$15Source09/08/2026
Moonshot AIVia OpenRoutermoonshotai/mxfp4$3$15Source09/08/2026
MorphVia OpenRoutermorph/fast$6$22.5Source09/08/2026
MorphVia OpenRoutermorph/fp4Lowest listed price: $2.5$14Source09/08/2026
ParasailVia OpenRouterparasail/fp4$3$15Source09/08/2026
PhalaVia OpenRouterphala$3$15Source09/08/2026
Sail ResearchVia OpenRoutersail-research/fp4$2.6$13Source09/08/2026
TogetherVia OpenRoutertogether$3$15Source09/08/2026
WaferVia OpenRouterwafer$3Lowest listed price: $12.75Source09/08/2026

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
GPT-5.5
Kimi K3
Coding: 78.7 / 87.1 (5 benchmark families)
Reasoning: 100 / 99.7 (1 benchmark family)
Knowledge: 100 / 99.8 (1 benchmark family)
Finance: 97.4 / 99.3 (5 benchmark families)
Legal: 75.3 / 99.8 (3 benchmark families)
Agentic tasks: 97.2 / 81 (2 benchmark families)
Multimodal: 100 / 99.9 (1 benchmark family)
Productivity: 89.2 / 100 (1 benchmark family)

27 matched rows from 25 benchmark families were considered. The radar shows 8 of 12 comparable categories.

GPT-5.5Kimi K3
AlmanBench v0.1Accepted cases. Higher is better. Test setup not documented as identical
GPT-5.5Higher measured value95.432 %
Kimi K390.962 %
Code MigrationOverall. Higher is better. No documented setup difference
GPT-5.5Winner45.161 %
Kimi K316.099 %
CorpFin v2Overall. Higher is better. No documented setup difference
GPT-5.568.415 %
Kimi K3Winner71.562 %
CyberBenchOverall. Higher is better. No documented setup difference
GPT-5.5Winner80.508 %
Kimi K379.026 %
EMBOverall. Higher is better. No documented setup difference
GPT-5.564.543 %
Kimi K3Winner66.399 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
GPT-5.551.76 %
Kimi K3Winner54.36 %
GPQA DiamondOverall. Higher is better. No documented setup difference
GPT-5.5Winner93.182 %
Kimi K392.929 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
GPT-5.53.75 %
Kimi K3Winner10.833 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
GPT-5.540.385 %
Kimi K3Winner44.231 %
LegalBenchOverall. Higher is better. No documented setup difference
GPT-5.5Winner86.515 %
Kimi K386.016 %
LiveCodeBench v6Overall. Higher is better. No documented setup difference
GPT-5.585.296 %
Kimi K3Winner87.185 %
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
GPT-5.51,477.235
Kimi K3Higher measured value1,489.017

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for GPT-5.5 and Kimi K3
Benchmark and taskGPT-5.5Kimi K3Source
AlmanBench v0.1Accepted cases
Test details
Test setup not documented as identicalNo direct winnerVersion: v0.1, results commit f34ddbfMetric: accepted casesScoring: Higher is betterGPT-5.5: Reasoning: xhigh
Kimi K3: Reasoning: max
1,029 public tasks with one direct run per row. The target is the Alman language specification.
Higher measured value95.432 %
90.962 %
Alman Institut
Source details
Data as of: 08/05/2026
Code MigrationOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner45.161 %
16.099 %
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 better
68.415 %
Winner71.562 %
Vals AI
Source details
Data as of: 08/12/2026
CyberBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner80.508 %
79.026 %
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
64.543 %
Winner66.399 %
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 better
51.76 %
Winner54.36 %
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 better
Winner93.182 %
92.929 %
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
3.75 %
Winner10.833 %
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 better
40.385 %
Winner44.231 %
Vals AI
Source details
Data as of: 09/03/2026
LegalBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner86.515 %
86.016 %
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
85.296 %
Winner87.185 %
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-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style control
GPT-5.5: Style-controlled Arena rating from 64,686 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 17,895 anonymous pairwise votes.
1,477.235
95% confidence interval: ±3.839The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Higher measured value1,489.017
95% confidence interval: ±5.47The 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
MedCodeOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner49.1 %
48.884 %
Vals AI
Source details
Data as of: 09/03/2026
MedScribeOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
86.868 %
Winner87.958 %
Vals AI
Source details
Data as of: 09/03/2026
MMLU-ProOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner88.144 %
87.973 %
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
Winner88.266 %
88.15 %
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
Winner68.76 %
66.336 %
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
0.5 %
Winner2 %
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
60.893 %
Winner68.268 %
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
51.532 %
Winner54.26 %
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 better
82.6 %
Winner93.4 %
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
74.98 %
Winner75.716 %
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
76.404 %
Winner80.899 %
Vals AI
Source details
Data as of: 09/03/2026
Time Horizon Index: KSPOverall
Test details
No documented difference in the test setupVersion: 1Metric: progressScoring: Higher is better
Winner8.333 %
5.167 %
Vals AI
Source details
Data as of: 08/20/2026
Vals IndexOverall
Test details
No documented difference in the test setupVersion: 2Metric: weighted index scoreScoring: Higher is better
57.411 %
Winner57.813 %
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 better
68.071 %
Winner73.42 %
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 betterSettings: Harness: OpenHands
69.847 %
Winner84.963 %
Vals AI
Source details
Data as of: 09/03/2026
CorpFin v2Exact Pages
Test details
Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGPT-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
65.618 %
Higher measured value69.347 %
Vals AI
Source details
Data as of: 08/06/2026
CyberBenchPatch
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterKimi K3: Temperature: 1, Output limit: 262,144 tokens
81.356 %
Higher measured value83.051 %
Vals AI
Source details
Data as of: 08/03/2026
EMBComps
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
64.681 %
Higher measured value72.685 %
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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
45.74 %
Higher measured value51.461 %
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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
No direct winner93.434 %
No direct winner93.434 %
Vals AI
Source details
Data as of: 08/09/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passed
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterGPT-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
82.246 %
Higher measured value87.319 %
Vals AI
Source details
Data as of: 08/07/2026
Legal Research BenchAdministrative / Regulatory · All-pass
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterGPT-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
53.03 %
Higher measured value54.545 %
Vals AI
Source details
Data as of: 08/06/2026
LegalBenchConclusion Tasks
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
89.644 %
Higher measured value90.733 %
Vals AI
Source details
Data as of: 08/09/2026
LiveCodeBench v6Easy
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
98.447 %
Higher measured value98.758 %
Vals AI
Source details
Data as of: 08/09/2026
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-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style control
GPT-5.5: Style-controlled Arena rating from 63,265 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 17,895 anonymous pairwise votes.
1,482.334
95% confidence interval: ±3.856The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Higher measured value1,489.017
95% confidence interval: ±5.47The 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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
Higher measured value94.003 %
93.863 %
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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
76.153 %
Higher measured value78.855 %
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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
9.5 %
Higher measured value17.5 %
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-5.5: Reasoning: xhigh, Temperature: 1, Output limit: 30,000 tokens
Kimi K3: Temperature: 1, Output limit: 30,000 tokens
40.476 %
Higher measured value44.048 %
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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
91.753 %
Higher measured value92.268 %
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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
Higher measured value65.495 %
65.331 %
Vals AI
Source details
Data as of: 08/09/2026
Terminal-Bench 2.1Easy
Test details
Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterGPT-5.5: Reasoning: high, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
83.333 %
Higher measured value91.667 %
Vals AI
Source details
Data as of: 08/06/2026
Time Horizon Index: KSPProgress efficiency
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: progressScoring: Higher is betterGPT-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
Higher measured value6.032 %
4.072 %
Vals AI
Source details
Data as of: 08/05/2026
Vals IndexCorpFin v2
Test details
Test setup not documented as identicalNo direct winnerVersion: 1.2Metric: benchmark scoreScoring: Higher is betterGPT-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
69.58 %
Higher measured value72.611 %
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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
69.58 %
Higher measured value72.611 %
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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
70.047 %
Higher measured value72.727 %
Vals AI
Source details
Data as of: 08/06/2026
CyberBenchPoC
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterKimi K3: Temperature: 1, Output limit: 262,144 tokens
Higher measured value79.661 %
75 %
Vals AI
Source details
Data as of: 08/03/2026
EMBDataroom
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
81.227 %
Higher measured value85.13 %
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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
39.562 %
Higher measured value41.69 %
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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
Higher measured value92.929 %
92.424 %
Vals AI
Source details
Data as of: 08/09/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Task fully resolved
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterGPT-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
No direct winner0 %
No direct winner0 %
Vals AI
Source details
Data as of: 08/07/2026
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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
86.669 %
Higher measured value90.731 %
Vals AI
Source details
Data as of: 08/06/2026
LegalBenchInterpretation Tasks
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
Higher measured value83.836 %
82.612 %
Vals AI
Source details
Data as of: 08/09/2026
LiveCodeBench v6Hard
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
69.714 %
Higher measured value74.286 %
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-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Kimi K3: Snapshot: kimi-k3-max, Reasoning: max, Harness: Arena text, style control
GPT-5.5: Style-controlled Arena rating from 12,904 anonymous pairwise votes.Kimi K3: Style-controlled Arena rating from 3,520 anonymous pairwise votes.
1,485.915
95% confidence interval: ±6.577The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Higher measured value1,489.216
95% confidence interval: ±10.41The 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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
No direct winner92.015 %
No direct winner92.015 %
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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
Higher measured value61.367 %
53.816 %
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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
0.5 %
Higher measured value2 %
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-5.5: Reasoning: xhigh, Temperature: 1
Kimi K3: Temperature: 1, Output limit: 30,000 tokens
72.222 %
Higher measured value75.617 %
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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
No direct winner66.667 %
No direct winner66.667 %
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-5.5: Reasoning: xhigh, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
84.464 %
Higher measured value86.1 %
Vals AI
Source details
Data as of: 08/09/2026
Terminal-Bench 2.1Hard
Test details
Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterGPT-5.5: Reasoning: high, Output limit: 128,000 tokens
Kimi K3: Temperature: 1, Output limit: 262,144 tokens
66.667 %
Higher measured value74.444 %
Vals AI
Source details
Data as of: 08/06/2026

Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Community tests you can inspect

Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.

Pelican on a bicycle

A community classic for free-form SVG drawing.

GPT-5.5

The API response was not fully received. The model was not evaluated.

First attempt
Run date
7 Sept 2026
API provider
openrouter
Requested API model
openai/gpt-5.5
Pinned endpoint
OpenAI | openai/gpt-5.5-20260423
Reasoning setting
high
Temperature
Provider default
Token limit including reasoning
8,192 tokens
Test protocol
community-visual-tests-v1
Technical checks
Failed

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Kimi K3

API access was unavailable for this run. The model was not evaluated.

First attempt
Run date
7 Sept 2026
API provider
openrouter
Requested API model
moonshotai/kimi-k3
Pinned endpoint
Moonshot AI | moonshotai/kimi-k3-20260715
Reasoning setting
high
Temperature
Provider default
Token limit including reasoning
8,192 tokens
Test protocol
community-visual-tests-v1
Technical checks
Not run

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Prompt and test conditions

Generate an SVG of a pelican riding a bicycle

Token limit including reasoning: 8,192 tokens

Task origin (Simon Willison)

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

Compare GPT-5.5 and Kimi K3 with other leading models using the same data and benchmark logic.

View the complete LLM comparison