Skip to main content

Head-to-head comparison

Claude Fable 5 vs. Claude Sonnet 5

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

shared result series
197
distinct benchmarks
25
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 Fable 5 and Claude Sonnet 5
AttributeClaude Fable 5Claude Sonnet 5
ProviderAnthropicAnthropic
ReleasedJun 9, 2026Jun 30, 2026
AvailabilityActiveActive
Model typeProprietaryProprietary
ParametersNot publishedNot published
ArchitectureNot publishedNot published
Context window1,000,000 tokens1,000,000 tokens
Knowledge cutoffJanuary 2026January 2026
Technical sourcesModel, Context, Knowledge cutoffModel, Context

Pricing

API pricing compared

The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.

API pricing for Claude Fable 5 and Claude Sonnet 5
Price typeClaude Fable 5Claude Sonnet 5
API input$10$2
API output$50$10
Cache read$1$0.2
Cache write (5 min.)$12.5$2.5
Cache write (1 hr.)$20$4
Price verified07/30/2026 Source09/02/2026 Source
Claude Fable 5Claude Sonnet 5
API inputUSD per 1M tokens, base tier
Claude Fable 5$10
Claude Sonnet 5Lower price$2
API outputUSD per 1M tokens, base tier
Claude Fable 5$50
Claude Sonnet 5Lower price$10
Cache readUSD per 1M tokens, base tier
Claude Fable 5$1
Claude Sonnet 5Lower 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 Claude Fable 5 and Claude Sonnet 5
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
Claude Fable 5AnthropicDirect from developerStandard APILowest listed price: $10Lowest listed price: $50Source07/30/2026
Amazon BedrockVia OpenRouteramazon-bedrockLowest listed price: $10Lowest listed price: $50Source09/07/2026
AnthropicVia OpenRouteranthropicLowest listed price: $10Lowest listed price: $50Source09/07/2026
AzureVia OpenRouterazureLowest listed price: $10Lowest listed price: $50Source09/07/2026
Claude Platform on AWSVia OpenRouterclaude-on-awsLowest listed price: $10Lowest listed price: $50Source09/07/2026
GoogleVia OpenRoutergoogle-vertex/europe$11$55Source09/07/2026
GoogleVia OpenRoutergoogle-vertex/globalLowest listed price: $10Lowest listed price: $50Source09/07/2026
Claude Sonnet 5AnthropicDirect from developerStandard APILowest listed price: $2Lowest listed price: $10Source09/02/2026
Amazon BedrockVia OpenRouteramazon-bedrock/globalLowest listed price: $2Lowest listed price: $10Source09/07/2026
Amazon BedrockVia OpenRouteramazon-bedrock/us-east-1$2.2$11Source09/07/2026
AnthropicVia OpenRouteranthropicLowest listed price: $2Lowest listed price: $10Source09/07/2026
AzureVia OpenRouterazure/globalLowest listed price: $2Lowest listed price: $10Source09/07/2026
AzureVia OpenRouterazure/usLowest listed price: $2Lowest listed price: $10Source09/07/2026
Claude Platform on AWSVia OpenRouterclaude-on-awsLowest listed price: $2Lowest listed price: $10Source09/07/2026
GoogleVia OpenRoutergoogle-vertex/europe$2.2$11Source09/07/2026
GoogleVia OpenRoutergoogle-vertex/globalLowest listed price: $2Lowest listed price: $10Source09/07/2026
GoogleVia OpenRoutergoogle-vertex/us$2.2$11Source09/07/2026

Performance

Shared benchmarks

Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.

Capability profile from matched benchmarks

Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.

255075100CodingReasoningMathematicsKnowledgeFinanceLegalAgentic tasksMultimodal
Claude Fable 5
Claude Sonnet 5
Coding: 97.5 / 76.1 (5 benchmark families)
Reasoning: 100 / 95.4 (1 benchmark family)
Mathematics: 100 / 81.1 (1 benchmark family)
Knowledge: 100 / 95.6 (1 benchmark family)
Finance: 99.1 / 95.3 (5 benchmark families)
Legal: 99.3 / 91.5 (3 benchmark families)
Agentic tasks: 100 / 92.6 (1 benchmark family)
Multimodal: 100 / 92.9 (1 benchmark family)

163 matched rows from 24 benchmark families were considered. The radar shows 8 of 12 comparable categories.

Claude Fable 5Claude Sonnet 5
Code MigrationOverall. Higher is better. No documented setup difference
Claude Fable 5Winner55.065 %
Claude Sonnet 544.392 %
CorpFin v2Overall. Higher is better. No documented setup difference
Claude Fable 5Winner71.834 %
Claude Sonnet 566.977 %
EMBOverall. Higher is better. No documented setup difference
Claude Fable 5Winner73.666 %
Claude Sonnet 566.316 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
Claude Fable 5Winner56.314 %
Claude Sonnet 553.909 %
GPQA DiamondOverall. Higher is better. No documented setup difference
Claude Fable 5Winner93.182 %
Claude Sonnet 588.889 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
Claude Fable 5Winner11.25 %
Claude Sonnet 55 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
Claude Fable 5Winner49.519 %
Claude Sonnet 541.827 %
LegalBenchOverall. Higher is better. No documented setup difference
Claude Fable 5Winner88.561 %
Claude Sonnet 583.922 %
LiveCodeBench v6Overall. Higher is better. No documented setup difference
Claude Fable 5Winner89.778 %
Claude Sonnet 582.429 %
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
Claude Fable 5Higher measured value1,507.405
Claude Sonnet 51,462.16
MedCodeOverall. Higher is better. No documented setup difference
Claude Fable 5Winner56.07 %
Claude Sonnet 547.54 %
MedScribeOverall. Higher is better. No documented setup difference
Claude Fable 5Winner88.522 %
Claude Sonnet 576.054 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Fable 5 and Claude Sonnet 5
Benchmark and taskClaude Fable 5Claude Sonnet 5Source
Code MigrationOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner55.065 %
44.392 %
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
Winner71.834 %
66.977 %
Vals AI
Source details
Data as of: 08/12/2026
EMBOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner73.666 %
66.316 %
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
Winner56.314 %
53.909 %
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 %
88.889 %
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
Winner11.25 %
5 %
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
Winner49.519 %
41.827 %
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
Winner88.561 %
83.922 %
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
Winner89.778 %
82.429 %
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 Fable 5: Snapshot: claude-fable-5, Harness: Arena text, style control
Claude Sonnet 5: Snapshot: claude-sonnet-5-high, Reasoning: high, Harness: Arena text, style controlClaude Fable 5: Style-controlled Arena rating from 26,977 anonymous pairwise votes.Claude Sonnet 5: Style-controlled Arena rating from 31,096 anonymous pairwise votes.
Higher measured value1,507.405
95% confidence interval: ±4.978The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,462.16
95% confidence interval: ±4.745The 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
Winner56.07 %
47.54 %
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
Winner88.522 %
76.054 %
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
Winner91.502 %
87.545 %
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
Winner89.306 %
83.006 %
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
68.919 %
Winner70.032 %
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
Winner2 %
0 %
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
Winner95 %
77 %
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
Winner70.433 %
66.035 %
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
Winner51.89 %
48.925 %
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
Winner95 %
79.6 %
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
Winner76.942 %
75.634 %
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
Winner80.524 %
74.532 %
Vals AI
Source details
Data as of: 09/03/2026
Vals IndexOverall
Test details
No documented difference in the test setupVersion: 2Metric: weighted index scoreScoring: Higher is better
Winner66.036 %
59.61 %
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
Winner74.154 %
68.826 %
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
Winner90.352 %
81.325 %
Vals AI
Source details
Data as of: 09/03/2026
Code MigrationCLI
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner60.087 %
36.332 %
Vals AI
Source details
Data as of: 08/09/2026
CorpFin v2Exact Pages
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner66.9 %
63.869 %
Vals AI
Source details
Data as of: 08/06/2026
EMBComps
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner70.785 %
69.384 %
Vals AI
Source details
Data as of: 08/06/2026
Finance Agent (v2)Adjustments
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner51.092 %
48.715 %
Vals AI
Source details
Data as of: 08/06/2026
GPQA DiamondFew-Shot CoT
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner92.929 %
87.374 %
Vals AI
Source details
Data as of: 08/09/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passed
Test details
No documented difference in the test setupVersion: 1Metric: criteria pass rateScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner92.035 %
88.768 %
Vals AI
Source details
Data as of: 08/07/2026
Legal Research BenchAdministrative / Regulatory · All-pass
Test details
No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner57.576 %
54.545 %
Vals AI
Source details
Data as of: 08/06/2026
LegalBenchConclusion Tasks
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner91.775 %
89.555 %
Vals AI
Source details
Data as of: 08/09/2026
LiveCodeBench v6Easy
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner98.758 %
98.447 %
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 betterClaude Fable 5: Snapshot: claude-fable-5, Harness: Arena text, style control
Claude Sonnet 5: Snapshot: claude-sonnet-5-high, Reasoning: high, Harness: Arena text, style controlClaude Fable 5: Style-controlled Arena rating from 5,567 anonymous pairwise votes.Claude Sonnet 5: Style-controlled Arena rating from 6,214 anonymous pairwise votes.
Higher measured value1,501.942
95% confidence interval: ±8.642The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,462.981
95% confidence interval: ±8.229The 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
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Tie93.584 %
Tie93.584 %
Vals AI
Source details
Data as of: 08/09/2026
MortgageTaxNumerical Extraction
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
76.709 %
Winner78.696 %
Vals AI
Source details
Data as of: 08/09/2026
ProgramBenchAlmost Resolved
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner33 %
13.5 %
Vals AI
Source details
Data as of: 08/09/2026
SAGEAutomata
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 30,000 tokens
Winner39.682 %
34.92 %
Vals AI
Source details
Data as of: 08/09/2026
SWE-bench Verified<15 min fix
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner95.876 %
83.505 %
Vals AI
Source details
Data as of: 08/08/2026
TaxEval v2Correctness
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner65.822 %
64.023 %
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 Sonnet 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
No direct winner100 %
No direct winner100 %
Vals AI
Source details
Data as of: 08/06/2026
Vals IndexCorpFin v2
Test details
No documented difference in the test setupVersion: 1.2Metric: benchmark scoreScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner71.562 %
67.949 %
Vals AI
Source details
Data as of: 08/09/2026
Vals Multimodal IndexCorpFin v2
Test details
No documented difference in the test setupVersion: 1.2Metric: benchmark scoreScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner71.562 %
67.949 %
Vals AI
Source details
Data as of: 08/09/2026
Code MigrationCOBOL
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
40 %
Winner68.571 %
Vals AI
Source details
Data as of: 08/09/2026
CorpFin v2Max Fitting Context
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner77.04 %
69.114 %
Vals AI
Source details
Data as of: 08/06/2026
EMBDataroom
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner85.362 %
84.909 %
Vals AI
Source details
Data as of: 08/06/2026
Finance Agent (v2)All-Pass
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner45.694 %
42.084 %
Vals AI
Source details
Data as of: 08/06/2026
GPQA DiamondZero-Shot CoT
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner93.434 %
90.404 %
Vals AI
Source details
Data as of: 08/09/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Task fully resolved
Test details
No documented difference in the test setupVersion: 1Metric: task resolution rateScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Tie0 %
Tie0 %
Vals AI
Source details
Data as of: 08/07/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit
Test details
No documented difference in the test setupVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner90.224 %
87.81 %
Vals AI
Source details
Data as of: 08/06/2026
LegalBenchInterpretation Tasks
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner86.863 %
81.412 %
Vals AI
Source details
Data as of: 08/09/2026
LiveCodeBench v6Hard
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner79.714 %
66.857 %
Vals AI
Source details
Data as of: 08/09/2026
LMArena Text, Style ControlChinese
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Fable 5: Snapshot: claude-fable-5, Harness: Arena text, style control
Claude Sonnet 5: Snapshot: claude-sonnet-5-high, Reasoning: high, Harness: Arena text, style controlClaude Fable 5: Style-controlled Arena rating from 1,671 anonymous pairwise votes.Claude Sonnet 5: Style-controlled Arena rating from 2,074 anonymous pairwise votes.
Higher measured value1,554.267
95% confidence interval: ±15.295The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,499.492
95% confidence interval: ±13.64The 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
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner93.156 %
91.635 %
Vals AI
Source details
Data as of: 08/09/2026
MortgageTaxSemantic Extraction
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
61.129 %
Winner61.367 %
Vals AI
Source details
Data as of: 08/09/2026
ProgramBenchFully Resolved
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner2 %
0 %
Vals AI
Source details
Data as of: 08/09/2026
SAGELinear Algebra
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 30,000 tokens
Winner71.544 %
68.999 %
Vals AI
Source details
Data as of: 08/09/2026
SWE-bench Verified>4 hours
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner100 %
66.667 %
Vals AI
Source details
Data as of: 08/08/2026
TaxEval v2Stepwise Reasoning
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner88.062 %
87.244 %
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 betterClaude Sonnet 5: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Higher measured value70 %
57.778 %
Vals AI
Source details
Data as of: 08/06/2026
Vals IndexFinance Agent v2
Test details
No documented difference in the test setupVersion: 1.2Metric: benchmark scoreScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner56.349 %
51.979 %
Vals AI
Source details
Data as of: 08/09/2026
Vals Multimodal IndexFinance Agent v2
Test details
No documented difference in the test setupVersion: 1.2Metric: benchmark scoreScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
Winner56.349 %
51.979 %
Vals AI
Source details
Data as of: 08/09/2026
Code MigrationCode Quality
Test details
No documented difference in the test setupVersion: 1Metric: mean reviewer code-quality ratingScoring: Higher is betterSettings: Compute: max, Temperature: 1, Output limit: 128,000 tokens
4.442 / 5
Winner4.898 / 5
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 Claude Fable 5 and Claude Sonnet 5 with other leading models using the same data and benchmark logic.

View the complete LLM comparison