Skip to main content

Head-to-head comparison

Claude Opus 5 vs. GPT-5.6 Sol

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

shared result series
247
distinct benchmarks
34
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 Claude Opus 5 and GPT-5.6 Sol
AttributeClaude Opus 5GPT-5.6 Sol
ProviderAnthropicOpenAI
ReleasedJul 24, 2026Jun 26, 2026
AvailabilityActiveActive
Model typeProprietaryProprietary
ParametersNot publishedNot published
ArchitectureNot publishedNot published
Context window1,000,000 tokens1,050,000 tokens
Knowledge cutoffMay 2026February 16, 2026
Technical sourcesModel, Knowledge cutoffModel, Context, Knowledge cutoff

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 Claude Opus 5 and GPT-5.6 Sol
Price typeClaude Opus 5GPT-5.6 Sol
API input$5$4 ≤272K / $8 >272K
API output$25$20 ≤272K / $30 >272K
Cache read$0.5$0.4 ≤272K / $0.8 >272K
Cache write (5 min.)$6.25$5 ≤272K / $10 >272K
Cache write (1 hr.)$10Not listed
Price verified07/30/2026 Source08/24/2026 Source
Claude Opus 5GPT-5.6 Sol
API inputUSD per 1M tokens, base tier
Claude Opus 5$5
GPT-5.6 SolLower price$4
API outputUSD per 1M tokens, base tier
Claude Opus 5$25
GPT-5.6 SolLower price$20
Cache readUSD per 1M tokens, base tier
Claude Opus 5$0.5
GPT-5.6 SolLower price$0.4

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 Claude Opus 5 and GPT-5.6 Sol
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
Claude Opus 5AnthropicDirect from developerStandard APILowest listed price: $5Lowest listed price: $25Source07/30/2026
Amazon BedrockVia OpenRouteramazon-bedrockLowest listed price: $5Lowest listed price: $25Source09/06/2026
Amazon BedrockVia OpenRouteramazon-bedrock/us-east-1$5.5$27.5Source09/06/2026
AnthropicVia OpenRouteranthropicLowest listed price: $5Lowest listed price: $25Source09/06/2026
AnthropicVia OpenRouteranthropic/fast$10$50Source09/06/2026
AzureVia OpenRouterazure/globalLowest listed price: $5Lowest listed price: $25Source09/06/2026
AzureVia OpenRouterazure/usLowest listed price: $5Lowest listed price: $25Source09/06/2026
Claude Platform on AWSVia OpenRouterclaude-on-awsLowest listed price: $5Lowest listed price: $25Source09/06/2026
GoogleVia OpenRoutergoogle-vertex/europe$5.5$27.5Source09/06/2026
GoogleVia OpenRoutergoogle-vertex/globalLowest listed price: $5Lowest listed price: $25Source09/06/2026
GoogleVia OpenRoutergoogle-vertex/us$5.5$27.5Source09/06/2026
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$22Source09/06/2026
AzureVia OpenRouterazure$5$30Source09/06/2026
AzureVia OpenRouterazure/eu$5.5$33Source09/06/2026
AzureVia OpenRouterazure/us$5.5$33Source09/06/2026
OpenAIVia OpenRouteropenai$2$10Source09/06/2026
OpenAIVia OpenRouteropenai/fast$4$20Source09/06/2026
OpenAIVia OpenRouteropenai/flexLowest listed price: $1Lowest listed price: $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
Claude Opus 5
GPT-5.6 Sol
Coding: 100 / 86.6 (6 benchmark families)
Reasoning: 98.1 / 100 (1 benchmark family)
Mathematics: 100 / 83.8 (1 benchmark family)
Knowledge: 95.7 / 98.6 (2 benchmark families)
Finance: 100 / 94.2 (5 benchmark families)
Legal: 100 / 74.8 (3 benchmark families)
Agentic tasks: 99.7 / 72.9 (4 benchmark families)
Multimodal: 100 / 98.8 (1 benchmark family)

37 matched rows from 33 benchmark families were considered. The radar shows 8 of 14 comparable categories.

Claude Opus 5GPT-5.6 Sol
AlmanBench v0.1Accepted cases. Higher is better. No documented setup difference
Claude Opus 594.947 %
GPT-5.6 SolWinner95.141 %
ARC-AGI-3RHAE overall score. Higher is better. No documented setup difference
Claude Opus 5Winner30.16 %
GPT-5.6 Sol2.15 %
BioMysteryBenchOverall. Higher is better. No documented setup difference
Claude Opus 5Winner79.259 %
GPT-5.6 Sol71.111 %
Code MigrationOverall. Higher is better. No documented setup difference
Claude Opus 5Winner57.473 %
GPT-5.6 Sol52.916 %
CorpFin v2Overall. Higher is better. No documented setup difference
Claude Opus 5Winner73.194 %
GPT-5.6 Sol64.375 %
CyberBenchOverall. Higher is better. No documented setup difference
Claude Opus 540.678 %
GPT-5.6 SolWinner88.136 %
EMBOverall. Higher is better. No documented setup difference
Claude Opus 5Winner73.556 %
GPT-5.6 Sol72.339 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
Claude Opus 5Winner58.633 %
GPT-5.6 Sol53.756 %
GPQA DiamondOverall. Higher is better. No documented setup difference
Claude Opus 593.434 %
GPT-5.6 SolWinner95.202 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
Claude Opus 5Winner6.667 %
GPT-5.6 Sol2.5 %
IOIOverall. Higher is better. No documented setup difference
Claude Opus 5Winner91.667 %
GPT-5.6 Sol86.667 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
Claude Opus 5Winner55.288 %
GPT-5.6 Sol48.077 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Opus 5 and GPT-5.6 Sol
Benchmark and taskClaude Opus 5GPT-5.6 SolSource
AlmanBench v0.1Accepted cases
Test details
No documented difference in the test setupVersion: v0.1, results commit f34ddbfMetric: accepted casesScoring: Higher is betterSettings: Reasoning: max1,029 public tasks with one direct run per row. The target is the Alman language specification.
94.947 %
Winner95.141 %
Alman Institut
Source details
Data as of: 08/05/2026
ARC-AGI-3RHAE overall score
Test details
No documented difference in the test setupVersion: ARC-AGI-3 2026 verifiedMetric: RHAE scoreScoring: Higher is betterSettings: Reasoning: high, Agent: ARC Prize official harness, Harness: ARC Prize official harnessOfficial ARC Prize harness on unseen interactive environments. Reasoning levels remain separate.
Winner30.16 %
2.15 %
ARC Prize, ARC Prize
Source details
Data as of: 08/26/2026
BioMysteryBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Harness: Terminus 2
Winner79.259 %
71.111 %
Vals AI
Source details
Data as of: 09/02/2026
Code MigrationOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner57.473 %
52.916 %
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
Winner73.194 %
64.375 %
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
40.678 %
Winner88.136 %
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
Winner73.556 %
72.339 %
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
Winner58.633 %
53.756 %
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
93.434 %
Winner95.202 %
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
Winner6.667 %
2.5 %
Vals AI
Source details
Data as of: 09/03/2026
IOIOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner91.667 %
86.667 %
Vals AI
Source details
Data as of: 08/09/2026
Legal Research BenchOverall · All-pass
Test details
No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is better
Winner55.288 %
48.077 %
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
Winner86.974 %
86.965 %
Vals AI
Source details
Data as of: 09/01/2026
LiveCodeBench v6Overall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner89.033 %
82.604 %
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 betterClaude Opus 5: Snapshot: claude-opus-5-high, Reasoning: high, Harness: Arena text, style control
GPT-5.6 Sol: Snapshot: gpt-5.6-sol-xhigh, Reasoning: xhigh, Harness: Arena text, style controlClaude Opus 5: Style-controlled Arena rating from 34,617 anonymous pairwise votes.GPT-5.6 Sol: Style-controlled Arena rating from 23,153 anonymous pairwise votes.
Higher measured value1,492.042
95% confidence interval: ±4.567The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,482.868
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.		LMArena
Source details
Data as of: 09/01/2026
MedCodeOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner63.57 %
43.974 %
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
Winner90.985 %
85.233 %
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
Winner91.591 %
89.1 %
Vals AI
Source details
Data as of: 09/01/2026
MMMU-ProOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner89.884 %
88.844 %
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
Winner72.059 %
67.289 %
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
Winner3 %
1.5 %
Vals AI
Source details
Data as of: 09/01/2026
ProofBenchOverall
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is better
Winner99 %
83 %
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
Winner76.928 %
66.509 %
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
49.426 %
Winner52.563 %
Vals AI
Source details
Data as of: 09/03/2026
SimpleQA Verified v2Kaggle score
Test details
No documented difference in the test setupNo clear leadVersion: Kaggle leaderboard 2026-08-03Metric: Kaggle leaderboard scoreScoring: Higher is better1,000 verified prompts without tools. Kaggle independently reproduced the results.
63.3 %
95% confidence interval: ±3.2
No clear lead69.2 %
95% confidence interval: ±2.9		Kaggle
Source details
Data as of: 08/03/2026
SkillsBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands
Winner60.441 %
54.1 %
Vals AI
Source details
Data as of: 09/01/2026
SRE BenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
12.214 %
Winner30.534 %
Vals AI
Source details
Data as of: 09/01/2026
SWE-bench VerifiedOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner97 %
96.2 %
Vals AI
Source details
Data as of: 09/01/2026
TaxEval v2Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better
Winner75.143 %
74.775 %
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
84.644 %
Winner85.768 %
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
Winner13.667 %
13 %
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
Winner67.213 %
63.709 %
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
Winner73.896 %
72.64 %
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
Winner88.404 %
80.495 %
Vals AI
Source details
Data as of: 09/03/2026
ARC-AGI-3RHAE overall score
Test details
Test setup not documented as identicalNo direct winnerVersion: ARC-AGI-3 2026 verifiedMetric: RHAE scoreScoring: Higher is betterClaude Opus 5: Reasoning: high, Agent: ARC Prize official harness, Harness: ARC Prize official harness
GPT-5.6 Sol: Reasoning: low, Agent: ARC Prize official harness, Harness: ARC Prize official harnessOfficial ARC Prize harness on unseen interactive environments. Reasoning levels remain separate.
Higher measured value30.16 %
0.33 %
ARC Prize, ARC Prize
Source details
Data as of: 08/26/2026
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
Higher measured value53.297 %
47.221 %
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
Higher measured value68.648 %
61.538 %
Vals AI
Source details
Data as of: 08/06/2026
CyberBenchPatch
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
81.356 %
Winner83.051 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
Higher measured value75.171 %
71.309 %
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 betterClaude Opus 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
Higher measured value54.617 %
49.233 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
92.424 %
Higher measured value94.949 %
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
Higher measured value87.319 %
78.623 %
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 betterClaude Opus 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
Higher measured value100 %
85 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
Higher measured value65.152 %
60.606 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
Higher measured value91.56 %
90.492 %
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
Higher measured value99.068 %
98.137 %
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 betterClaude Opus 5: Snapshot: claude-opus-5-max, Reasoning: max, Harness: Arena text, style control
GPT-5.6 Sol: Snapshot: gpt-5.6-sol-xhigh, Reasoning: xhigh, Harness: Arena text, style controlClaude Opus 5: Style-controlled Arena rating from 16,839 anonymous pairwise votes.GPT-5.6 Sol: Style-controlled Arena rating from 23,153 anonymous pairwise votes.
Higher measured value1,487.8
95% confidence interval: ±5.818The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,482.868
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.		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
Higher measured value95.676 %
94.561 %
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
Higher measured value81.399 %
75.119 %
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
Higher measured value41.5 %
23 %
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 betterClaude Opus 5: Temperature: 1, Output limit: 30,000 tokens
GPT-5.6 Sol: Reasoning: max, Output limit: 30,000 tokens
32.54 %
Higher measured value39.682 %
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 betterClaude Opus 5: Compute: max, Harness: OpenHands, Temperature: 1, Output limit: 128,000 tokens
GPT-5.6 Sol: Reasoning: max, Harness: OpenHands, Output limit: 128,000 tokens
Higher measured value45.191 %
43.312 %
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
Higher measured value98.454 %
97.423 %
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
61.979 %
Higher measured value65.004 %
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 betterClaude Opus 5: Compute: high, Temperature: 1, Output limit: 128,000 tokens
GPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
Higher measured value100 %
91.667 %
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 betterClaude Opus 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
Higher measured value11.947 %
10.634 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
Higher measured value74.942 %
66.434 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
Higher measured value74.942 %
66.434 %
Vals AI
Source details
Data as of: 08/09/2026
ARC-AGI-3RHAE overall score
Test details
Test setup not documented as identicalNo direct winnerVersion: ARC-AGI-3 2026 verifiedMetric: RHAE scoreScoring: Higher is betterClaude Opus 5: Reasoning: high, Agent: ARC Prize official harness, Harness: ARC Prize official harness
GPT-5.6 Sol: Reasoning: max, Agent: ARC Prize official harness, Harness: ARC Prize official harnessOfficial ARC Prize harness on unseen interactive environments. Reasoning levels remain separate.
Higher measured value30.16 %
7.78 %
ARC Prize, ARC Prize
Source details
Data as of: 08/26/2026
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
No direct winner70 %
No direct winner70 %
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
Higher measured value75.991 %
65.152 %
Vals AI
Source details
Data as of: 08/06/2026
CyberBenchPoC
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
0 %
Winner93.22 %
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-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
Higher measured value87.681 %
85.243 %
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 betterClaude Opus 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
GPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens
Higher measured value47.708 %
41.362 %
Vals AI
Source details
Data as of: 08/06/2026

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 Claude Opus 5 and GPT-5.6 Sol with other leading models using the same data and benchmark logic.

View the complete LLM comparison