Skip to main content

Head-to-head comparison

GPT-5.4 vs. Grok 4.3

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

shared result series
181
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 and Grok 4.3
AttributeGPT-5.4Grok 4.3
ProviderOpenAIxAI
ReleasedMar 2026May 6, 2026
AvailabilityActiveActive
Model typeProprietaryProprietary
ParametersNot publishedNot published
ArchitectureNot publishedNot published
Context window1,050,000 tokens1,000,000 tokens
Knowledge cutoffAugust 31, 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-5.4 and Grok 4.3
Price typeGPT-5.4Grok 4.3
API input$2.5 ≤272K / $5 >272K$1.25 ≤200K / $2.5 >200K
API output$15 ≤272K / $22.5 >272K$2.5 ≤200K / $5 >200K
Cache read$0.25 ≤272K / $0.5 >272K$0.2 ≤200K / $0.4 >200K
Cache write (5 min.)Not listedNot listed
Cache write (1 hr.)Not listedNot listed
Price verified07/30/2026 Source08/11/2026 Source
GPT-5.4Grok 4.3
API inputUSD per 1M tokens, base tier
GPT-5.4$2.5
Grok 4.3Lower price$1.25
API outputUSD per 1M tokens, base tier
GPT-5.4$15
Grok 4.3Lower price$2.5
Cache readUSD per 1M tokens, base tier
GPT-5.4$0.25
Grok 4.3Lower price$0.2

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 and Grok 4.3
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
GPT-5.4OpenAIDirect from developerUp to 272,000 context tokens$2.5$15Source07/30/2026
OpenAIDirect from developerAbove 272,000 context tokens$5$22.5Source07/30/2026
Amazon BedrockVia OpenRouteramazon-bedrock/us-east-1$2.75$16.5Source09/06/2026
AzureVia OpenRouterazure$2.5$15Source09/06/2026
AzureVia OpenRouterazure/eu$2.75$16.5Source09/06/2026
AzureVia OpenRouterazure/us$2.75$16.5Source09/06/2026
OpenAIVia OpenRouteropenai$2.5$15Source09/06/2026
OpenAIVia OpenRouteropenai/fast$5$30Source09/06/2026
OpenAIVia OpenRouteropenai/flexLowest listed price: $1.25Lowest listed price: $7.5Source09/06/2026
Grok 4.3xAIDirect from developerUp to 200,000 context tokensLowest listed price: $1.25Lowest listed price: $2.5Source08/11/2026
xAIDirect from developerAbove 200,000 context tokens$2.5$5Source08/11/2026
xAIVia OpenRouterxaiLowest listed price: $1.25Lowest listed price: $2.5Source09/06/2026
xAIVia OpenRouterxai/priority$2.5$5Source09/06/2026
xAIVia OpenRouterxai/zdrLowest listed price: $1.25Lowest listed price: $2.5Source09/06/2026
xAIVia OpenRouterxai/zdr/priority$2.5$5Source09/06/2026

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.

255075100CodingReasoningMathematicsKnowledgeFinanceLegalAgentic tasksMultimodal
GPT-5.4
Grok 4.3
Coding: 99.9 / 65.8 (7 benchmark families)
Reasoning: 100 / 98.8 (2 benchmark families)
Mathematics: 100 / 97.4 (1 benchmark family)
Knowledge: 100 / 97.9 (2 benchmark families)
Finance: 98.8 / 91 (4 benchmark families)
Legal: 66.7 / 98.5 (3 benchmark families)
Agentic tasks: 100 / 76.5 (2 benchmark families)
Multimodal: 100 / 94.9 (1 benchmark family)

51 matched rows from 21 benchmark families were considered. The radar shows 8 of 12 comparable categories.

GPT-5.4Grok 4.3
Code MigrationOverall. Higher is better. No documented setup difference
GPT-5.4Winner34.984 %
Grok 4.36.795 %
CorpFin v2Overall. Higher is better. No documented setup difference
GPT-5.465.268 %
Grok 4.3Winner68.532 %
CyberBenchOverall. Higher is better. No documented setup difference
GPT-5.4Winner72.881 %
Grok 4.347.457 %
GPQA DiamondOverall. Higher is better. No documented setup difference
GPT-5.4Winner91.666 %
Grok 4.391.414 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
GPT-5.40 %
Grok 4.3Winner0.417 %
IOIOverall. Higher is better. No documented setup difference
GPT-5.4Winner67.834 %
Grok 4.315.334 %
LegalBenchOverall. Higher is better. No documented setup difference
GPT-5.4Winner86.044 %
Grok 4.384.458 %
LiveCodeBench v6Overall. Higher is better. No documented setup difference
GPT-5.484.141 %
Grok 4.3Winner84.494 %
LMArena Text, Style ControlOverall. Higher is better. No documented setup difference
GPT-5.4Winner1,465.527
Grok 4.31,442.599
MedCodeOverall. Higher is better. No documented setup difference
GPT-5.4Winner41.292 %
Grok 4.338.068 %
MedScribeOverall. Higher is better. No documented setup difference
GPT-5.4Winner77.549 %
Grok 4.374.399 %
MMLU-ProOverall. Higher is better. No documented setup difference
GPT-5.4Winner87.482 %
Grok 4.385.838 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for GPT-5.4 and Grok 4.3
Benchmark and taskGPT-5.4Grok 4.3Source
Code MigrationOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05
Winner34.984 %
6.795 %
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: Snapshot: gpt-5.4-2026-03-05
65.268 %
Winner68.532 %
Vals AI
Source details
Data as of: 08/12/2026
CyberBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05
Winner72.881 %
47.457 %
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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05
Winner91.666 %
91.414 %
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: Snapshot: gpt-5.4-2026-03-05
0 %
Winner0.417 %
Vals AI
Source details
Data as of: 09/03/2026
IOIOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05
Winner67.834 %
15.334 %
Vals AI
Source details
Data as of: 08/09/2026
LegalBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05
Winner86.044 %
84.458 %
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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05
84.141 %
Winner84.494 %
Vals AI
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlOverall
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Grok 4.3: Snapshot: grok-4.3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 63,615 anonymous pairwise votes.Grok 4.3: Style-controlled Arena rating from 65,024 anonymous pairwise votes.
Winner1,465.527
95% confidence interval: ±3.807The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,442.599
95% confidence interval: ±3.771The 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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05
Winner41.292 %
38.068 %
Vals AI
Source details
Data as of: 09/03/2026
MedScribeOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05
Winner77.549 %
74.399 %
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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05
Winner87.482 %
85.838 %
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: Snapshot: gpt-5.4-2026-03-05
Winner87.514 %
83.064 %
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: Snapshot: gpt-5.4-2026-03-05
Winner68.323 %
48.252 %
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: Snapshot: gpt-5.4-2026-03-05
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: Snapshot: gpt-5.4-2026-03-05
Winner43.312 %
19.736 %
Vals AI
Source details
Data as of: 09/03/2026
SkillsBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Harness: OpenHands
Grok 4.3: Harness: OpenHands
Winner51.711 %
40.638 %
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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05
Winner78.2 %
71.4 %
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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05
Winner73.958 %
70.81 %
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: Snapshot: gpt-5.4-2026-03-05
Winner58.427 %
43.446 %
Vals AI
Source details
Data as of: 06/04/2026
Vibe Code Bench v1.1Overall
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Harness: OpenHands
Grok 4.3: Harness: OpenHands
Winner67.421 %
19.403 %
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: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95
Higher measured value23.788 %
9.06 %
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: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
64.103 %
Higher measured value66.783 %
Vals AI
Source details
Data as of: 08/06/2026
CyberBenchPatch
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05
Winner81.356 %
64.407 %
Vals AI
Source details
Data as of: 08/03/2026
GPQA DiamondFew-Shot CoT
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
91.414 %
Higher measured value92.929 %
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-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95
Higher measured value76.449 %
61.594 %
Vals AI
Source details
Data as of: 08/07/2026
IOIIOI 2024
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95
Higher measured value67.167 %
13 %
Vals AI
Source details
Data as of: 08/09/2026
LegalBenchConclusion Tasks
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
88.939 %
Higher measured value89.912 %
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-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
Higher measured value99.068 %
98.447 %
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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Grok 4.3: Snapshot: grok-4.3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 60,657 anonymous pairwise votes.Grok 4.3: Style-controlled Arena rating from 65,024 anonymous pairwise votes.
Higher measured value1,476.488
95% confidence interval: ±3.881The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,442.599
95% confidence interval: ±3.771The 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: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
92.887 %
Higher measured value93.305 %
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: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95, Output limit: 256,000 tokens
Higher measured value75.994 %
37.52 %
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: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95
Higher measured value7 %
0 %
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: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 30,000 tokens
Grok 4.3: Temperature: 1, Top P: 0.95, Output limit: 30,000 tokens
21.428 %
Higher measured value35.318 %
Vals AI
Source details
Data as of: 08/09/2026
SkillsBenchNo Skills
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Harness: OpenHands, Output limit: 128,000 tokens
Grok 4.3: Reasoning: high, Harness: OpenHands, Temperature: 0.7, Top P: 0.95
Higher measured value48.905 %
19.305 %
Vals AI
Source details
Data as of: 08/07/2026
SWE-bench Verified<15 min fix
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95
Higher measured value88.144 %
83.505 %
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: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
Higher measured value64.922 %
60.589 %
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: Snapshot: gpt-5.4-2026-03-05, Reasoning: high, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
Higher measured value100 %
66.667 %
Vals AI
Source details
Data as of: 06/04/2026
Code MigrationCOBOL
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95
Higher measured value68.571 %
0 %
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: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
64.918 %
Higher measured value68.765 %
Vals AI
Source details
Data as of: 08/06/2026
CyberBenchPoC
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05
Winner64.407 %
30.508 %
Vals AI
Source details
Data as of: 08/03/2026
GPQA DiamondZero-Shot CoT
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
Higher measured value91.919 %
89.899 %
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-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95
No direct winner0 %
No direct winner0 %
Vals AI
Source details
Data as of: 08/07/2026
IOIIOI 2025
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95
Higher measured value68.5 %
17.667 %
Vals AI
Source details
Data as of: 08/09/2026
LegalBenchInterpretation Tasks
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
Higher measured value83.921 %
81.805 %
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-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
Higher measured value67.714 %
66 %
Vals AI
Source details
Data as of: 08/09/2026
LMArena Text, Style ControlBusiness, management and finance
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Grok 4.3: Snapshot: grok-4.3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 13,060 anonymous pairwise votes.Grok 4.3: Style-controlled Arena rating from 13,131 anonymous pairwise votes.
Winner1,474.871
95% confidence interval: ±6.534The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,439.103
95% confidence interval: ±6.526The 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: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
91.762 %
Higher measured value92.902 %
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: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95, Output limit: 256,000 tokens
Higher measured value60.652 %
58.983 %
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: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95
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: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 30,000 tokens
Grok 4.3: Temperature: 1, Top P: 0.95, Output limit: 30,000 tokens
Higher measured value70.988 %
48.148 %
Vals AI
Source details
Data as of: 08/09/2026
SkillsBenchWith Skills
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Harness: OpenHands, Output limit: 128,000 tokens
Grok 4.3: Reasoning: high, Harness: OpenHands, Temperature: 0.7, Top P: 0.95
Higher measured value51.711 %
40.638 %
Vals AI
Source details
Data as of: 08/07/2026
SWE-bench Verified>4 hours
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95
0 %
Higher measured value33.333 %
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: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
Higher measured value82.993 %
81.03 %
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: Snapshot: gpt-5.4-2026-03-05, Reasoning: high, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
Higher measured value33.333 %
24.444 %
Vals AI
Source details
Data as of: 06/04/2026
Code MigrationCode Quality
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: mean reviewer code-quality ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95
Higher measured value3.632 / 5
3.098 / 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: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
66.783 %
Higher measured value70.047 %
Vals AI
Source details
Data as of: 08/06/2026
Harvey's Legal Agent BenchmarkArbitration International Dispute Resolution · Criteria passed
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95
66.667 %
Higher measured value68.1 %
Vals AI
Source details
Data as of: 08/07/2026
LegalBenchIssue Tasks
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
Higher measured value90.526 %
89.182 %
Vals AI
Source details
Data as of: 08/09/2026
LiveCodeBench v6Medium
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
85.64 %
Higher measured value89.034 %
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: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Grok 4.3: Snapshot: grok-4.3, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 12,346 anonymous pairwise votes.Grok 4.3: Style-controlled Arena rating from 13,131 anonymous pairwise votes.
Higher measured value1,483.779
95% confidence interval: ±6.654The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,439.103
95% confidence interval: ±6.526The 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-ProChemistry
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Temperature: 0.7, Top P: 0.95
91.078 %
Higher measured value91.608 %
Vals AI
Source details
Data as of: 08/09/2026
ProgramBenchRaw Pass Rate
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Grok 4.3: Reasoning: high, Temperature: 0.7, Top P: 0.95
Higher measured value68.596 %
22.105 %
Vals AI
Source details
Data as of: 08/09/2026
SAGELinear Algebra
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 30,000 tokens
Grok 4.3: Temperature: 1, Top P: 0.95, Output limit: 30,000 tokens
Higher measured value68.826 %
18.334 %
Vals AI
Source details
Data as of: 08/09/2026

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 and Grok 4.3 with other leading models using the same data and benchmark logic.

View the complete LLM comparison