Skip to main content

Head-to-head comparison

GPT-5.6 Sol vs. GPT-5.4

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

shared result series
179
distinct benchmarks
22
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-5.6 Sol and GPT-5.4
AttributeGPT-5.6 SolGPT-5.4
ProviderOpenAIOpenAI
ReleasedJul 9, 2026Mar 5, 2026
AvailabilityActiveActive
Model typeProprietaryProprietary
ParametersNot publishedNot published
ArchitectureNot publishedNot published
Context window1,050,000 tokens1,050,000 tokens
Knowledge cutoffFebruary 16, 2026August 31, 2025
Technical sourcesModel, Context, Knowledge cutoffModel

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-5.6 Sol and GPT-5.4
Price typeGPT-5.6 SolGPT-5.4
API input$4 ≤272K / $8 >272K$2.5 ≤272K / $5 >272K
API output$20 ≤272K / $30 >272K$15 ≤272K / $22.5 >272K
Cache read$0.4 ≤272K / $0.8 >272K$0.25 ≤272K / $0.5 >272K
Cache write (5 min.)$5 ≤272K / $10 >272KNot listed
Cache write (1 hr.)Not listedNot listed
Price verified08/24/2026 Source07/30/2026 Source
GPT-5.6 SolGPT-5.4
API inputUSD per 1M tokens, base tier
GPT-5.6 Sol$4
GPT-5.4Lower price$2.5
API outputUSD per 1M tokens, base tier
GPT-5.6 Sol$20
GPT-5.4Lower price$15
Cache readUSD per 1M tokens, base tier
GPT-5.6 Sol$0.4
GPT-5.4Lower price$0.25

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-5.6 Sol and GPT-5.4
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
GPT-5.6 SolOpenAIDirect from developerUp to 272,000 context tokens$4$20Source08/24/2026
OpenAIDirect from developerAbove 272,000 context tokens$8$30Source08/24/2026
Amazon BedrockVia OpenRouteramazon-bedrock/us-east-1$4.4$22Source09/08/2026
AzureVia OpenRouterazure$5$30Source09/08/2026
AzureVia OpenRouterazure/eu$5.5$33Source09/08/2026
AzureVia OpenRouterazure/us$5.5$33Source09/08/2026
OpenAIVia OpenRouteropenai$2$10Source09/08/2026
OpenAIVia OpenRouteropenai/fast$4$20Source09/08/2026
OpenAIVia OpenRouteropenai/flexLowest listed price: $1Lowest listed price: $5Source09/08/2026
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$16.5Source09/08/2026
AzureVia OpenRouterazure$2.5$15Source09/08/2026
AzureVia OpenRouterazure/eu$2.75$16.5Source09/08/2026
AzureVia OpenRouterazure/us$2.75$16.5Source09/08/2026
OpenAIVia OpenRouteropenai$2.5$15Source09/08/2026
OpenAIVia OpenRouteropenai/fast$5$30Source09/08/2026
OpenAIVia OpenRouteropenai/flexLowest listed price: $1.25Lowest listed price: $7.5Source09/08/2026

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 tasksMultimodalCybersecurity
GPT-5.6 Sol
GPT-5.4
Coding: 99.7 / 68.2 (6 benchmark families)
Reasoning: 100 / 96.3 (1 benchmark family)
Knowledge: 100 / 98.2 (1 benchmark family)
Finance: 99 / 99.6 (3 benchmark families)
Legal: 100 / 49.5 (2 benchmark families)
Agentic tasks: 100 / 95.6 (1 benchmark family)
Multimodal: 100 / 98.5 (1 benchmark family)
Cybersecurity: 100 / 83.2 (1 benchmark family)

21 matched rows from 19 benchmark families were considered. The radar shows 8 of 10 comparable categories.

GPT-5.6 SolGPT-5.4
Code MigrationOverall. Higher is better. No documented setup difference
GPT-5.6 SolWinner52.916 %
GPT-5.434.984 %
CorpFin v2Overall. Higher is better. No documented setup difference
GPT-5.6 Sol64.375 %
GPT-5.4Winner65.268 %
CyberBenchOverall. Higher is better. No documented setup difference
GPT-5.6 SolWinner88.136 %
GPT-5.472.881 %
GPQA DiamondOverall. Higher is better. No documented setup difference
GPT-5.6 SolWinner95.202 %
GPT-5.491.666 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
GPT-5.6 SolWinner2.5 %
GPT-5.40 %
IOIOverall. Higher is better. No documented setup difference
GPT-5.6 SolWinner86.667 %
GPT-5.467.834 %
LegalBenchOverall. Higher is better. No documented setup difference
GPT-5.6 SolWinner86.965 %
GPT-5.486.044 %
LiveCodeBench v6Overall. Higher is better. No documented setup difference
GPT-5.6 Sol82.604 %
GPT-5.4Winner84.141 %
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
GPT-5.6 SolHigher measured value1,482.868
GPT-5.41,465.527
MedCodeOverall. Higher is better. No documented setup difference
GPT-5.6 SolWinner43.974 %
GPT-5.441.292 %
MedScribeOverall. Higher is better. No documented setup difference
GPT-5.6 SolWinner85.233 %
GPT-5.477.549 %
MMLU-ProOverall. Higher is better. No documented setup difference
GPT-5.6 SolWinner89.1 %
GPT-5.487.482 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for GPT-5.6 Sol and GPT-5.4
Benchmark and taskGPT-5.6 SolGPT-5.4Source
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
Winner52.916 %
34.984 %
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
64.375 %
Winner65.268 %
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
Winner88.136 %
72.881 %
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
Winner95.202 %
91.666 %
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
Winner2.5 %
0 %
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
Winner86.667 %
67.834 %
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
Winner86.965 %
86.044 %
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
82.604 %
Winner84.141 %
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-5.6 Sol: Snapshot: gpt-5.6-sol-xhigh, Reasoning: xhigh, Harness: Arena text, style control
GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
GPT-5.6 Sol: Style-controlled Arena rating from 23,153 anonymous pairwise votes.GPT-5.4: Style-controlled Arena rating from 63,615 anonymous pairwise votes.
Higher measured value1,482.868
95% confidence interval: ±5.12The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,465.527
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.
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
Winner43.974 %
41.292 %
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
Winner85.233 %
77.549 %
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
Winner89.1 %
87.482 %
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
Winner88.844 %
87.514 %
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
67.289 %
Winner68.323 %
Vals AI
Source details
Data as of: 09/01/2026
PRBench FinanceOverall
Test details
Test setup not documented as identicalNo direct winnerVersion: full finance setMetric: weighted rubric scoreScoring: Higher is betterGPT-5.6 Sol: Snapshot: gpt-5.6-sol-max, Reasoning: max, Attempts: pass@1
GPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Attempts: pass@1
600 finance tasks with task-specific rubrics and o4-mini as judge.
Higher measured value50.45% ± 0.33
95% confidence interval: ±0.33
45.63% ± 0.56
95% confidence interval: ±0.56
Scale AI
Source details
Data as of: 08/26/2026
PRBench LegalOverall
Test details
Test setup not documented as identicalNo direct winnerVersion: full legal setMetric: weighted rubric scoreScoring: Higher is betterGPT-5.6 Sol: Snapshot: gpt-5.6-sol-max, Reasoning: max, Attempts: pass@1
GPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Attempts: pass@1
500 legal tasks with task-specific rubrics and o4-mini as judge.
Higher measured value50.5% ± 0.54
95% confidence interval: ±0.54
44.35% ± 0.28
95% confidence interval: ±0.28
Scale AI
Source details
Data as of: 08/26/2026
ProgramBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05
Winner1.5 %
0 %
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
Winner52.563 %
43.312 %
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-5.6 Sol: Harness: OpenHands
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Harness: OpenHands
Winner54.1 %
51.711 %
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
Winner96.2 %
78.2 %
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: Snapshot: gpt-5.4-2026-03-05
Winner74.775 %
73.958 %
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 betterGPT-5.6 Sol: Harness: OpenHands
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Harness: OpenHands
Winner80.495 %
67.421 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value47.221 %
23.788 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
61.538 %
Higher measured value64.103 %
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
Winner83.051 %
81.356 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value94.949 %
91.414 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value78.623 %
76.449 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value85 %
67.167 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value90.492 %
88.939 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
98.137 %
Higher measured value99.068 %
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-5.6 Sol: Snapshot: gpt-5.6-sol-xhigh, Reasoning: xhigh, Harness: Arena text, style control
GPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
GPT-5.6 Sol: Style-controlled Arena rating from 23,153 anonymous pairwise votes.GPT-5.4: Style-controlled Arena rating from 60,657 anonymous pairwise votes.
Higher measured value1,482.868
95% confidence interval: ±5.12The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,476.488
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.
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value94.561 %
92.887 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
75.119 %
Higher measured value75.994 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value23 %
7 %
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-5.6 Sol: Reasoning: max, Output limit: 30,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 30,000 tokens
Higher measured value39.682 %
21.428 %
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-5.6 Sol: Reasoning: max, Harness: OpenHands, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Harness: OpenHands, Output limit: 128,000 tokens
43.312 %
Higher measured value48.905 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value97.423 %
88.144 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value65.004 %
64.922 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value70 %
68.571 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value65.152 %
64.918 %
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
Winner93.22 %
64.407 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value95.455 %
91.919 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value88.333 %
68.5 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value84.398 %
83.921 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
67.429 %
Higher measured value67.714 %
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-5.6 Sol: Snapshot: gpt-5.6-sol-xhigh, Reasoning: xhigh, Harness: Arena text, style control
GPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
GPT-5.6 Sol: Style-controlled Arena rating from 4,509 anonymous pairwise votes.GPT-5.4: Style-controlled Arena rating from 13,060 anonymous pairwise votes.
Higher measured value1,490.042
95% confidence interval: ±9.485The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,474.871
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.
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value93.283 %
91.762 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
59.459 %
Higher measured value60.652 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value1.5 %
0 %
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-5.6 Sol: Reasoning: max, Output limit: 30,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 30,000 tokens
67.284 %
Higher measured value70.988 %
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-5.6 Sol: Reasoning: max, Harness: OpenHands, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Harness: OpenHands, Output limit: 128,000 tokens
Higher measured value54.1 %
51.711 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value100 %
0 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value84.546 %
82.993 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value3.847 / 5
3.632 / 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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
66.434 %
Higher measured value66.783 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value82.079 %
66.667 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value91.438 %
90.526 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
82.245 %
Higher measured value85.64 %
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-5.6 Sol: Snapshot: gpt-5.6-sol-xhigh, Reasoning: xhigh, Harness: Arena text, style control
GPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
GPT-5.6 Sol: Style-controlled Arena rating from 4,509 anonymous pairwise votes.GPT-5.4: Style-controlled Arena rating from 12,346 anonymous pairwise votes.
Higher measured value1,490.042
95% confidence interval: ±9.485The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,483.779
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.
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value91.961 %
91.078 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value77.644 %
68.596 %
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-5.6 Sol: Reasoning: max, Output limit: 30,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 30,000 tokens
Higher measured value70.388 %
68.826 %
Vals AI
Source details
Data as of: 08/09/2026
SWE-bench Verified1-4 hours
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
GPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens
Higher measured value97.619 %
50 %
Vals AI
Source details
Data as of: 08/08/2026

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-5.6 Sol

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
openai/gpt-5.6-sol
Pinned endpoint
OpenAI | openai/gpt-5.6-sol-20260709
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.

GPT-5.4

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
openai/gpt-5.4
Pinned endpoint
OpenAI | openai/gpt-5.4-20260305
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-5.6 Sol and GPT-5.4 with other leading models using the same data and benchmark logic.

View the complete LLM comparison