Skip to main content

Head-to-head comparison

Claude Opus 5.5 vs. Claude Opus 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
22
distinct benchmarks
22
latest retrieval
2026-09-23

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 5.5 and Claude Opus 5
AttributeClaude Opus 5.5Claude Opus 5
ProviderAnthropicAnthropic
ReleasedSep 22, 2026Jul 24, 2026
AvailabilityActiveActive
Model typeProprietaryProprietary
ParametersNot publishedNot published
ArchitectureNot publishedNot published
Context window1,000,000 tokens1,000,000 tokens
Knowledge cutoffJune 2026May 2026
Technical sourcesModelModel, 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 5.5 and Claude Opus 5
Price typeClaude Opus 5.5Claude Opus 5
API input$4$5
API output$20$25
Cache read$0.2$0.5
Cache write (5 min.)$5$6.25
Cache write (1 hr.)$8$10
Price verified09/22/2026 Source09/22/2026 Source
Claude Opus 5.5Claude Opus 5
API inputUSD per 1M tokens, base tier
Claude Opus 5.5Lower price$4
Claude Opus 5$5
API outputUSD per 1M tokens, base tier
Claude Opus 5.5Lower price$20
Claude Opus 5$25
Cache readUSD per 1M tokens, base tier
Claude Opus 5.5Lower price$0.2
Claude Opus 5$0.5

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 5.5 and Claude Opus 5
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
Claude Opus 5.5AnthropicDirect from developerStandard APILowest listed price: $4Lowest listed price: $20Source09/22/2026
Amazon BedrockVia OpenRouteramazon-bedrockLowest listed price: $4Lowest listed price: $20Source09/23/2026
Amazon BedrockVia OpenRouteramazon-bedrock/eu-west-1$4.4$22Source09/23/2026
Amazon BedrockVia OpenRouteramazon-bedrock/us-east-1$4.4$22Source09/23/2026
AnthropicVia OpenRouteranthropicLowest listed price: $4Lowest listed price: $20Source09/23/2026
AnthropicVia OpenRouteranthropic/fast$8$40Source09/23/2026
AzureVia OpenRouterazure/globalLowest listed price: $4Lowest listed price: $20Source09/23/2026
AzureVia OpenRouterazure/us$4.4$22Source09/23/2026
Claude Platform on AWSVia OpenRouterclaude-on-awsLowest listed price: $4Lowest listed price: $20Source09/23/2026
GoogleVia OpenRoutergoogle-vertex/europe$4.4$22Source09/23/2026
GoogleVia OpenRoutergoogle-vertex/globalLowest listed price: $4Lowest listed price: $20Source09/23/2026
GoogleVia OpenRoutergoogle-vertex/us$4.4$22Source09/23/2026
Claude Opus 5AnthropicDirect from developerStandard APILowest listed price: $5Lowest listed price: $25Source09/22/2026
Amazon BedrockVia OpenRouteramazon-bedrockLowest listed price: $5Lowest listed price: $25Source09/23/2026
Amazon BedrockVia OpenRouteramazon-bedrock/eu-west-1$5.5$27.5Source09/23/2026
Amazon BedrockVia OpenRouteramazon-bedrock/us-east-1$5.5$27.5Source09/23/2026
AnthropicVia OpenRouteranthropicLowest listed price: $5Lowest listed price: $25Source09/23/2026
AnthropicVia OpenRouteranthropic/fast$10$50Source09/23/2026
AzureVia OpenRouterazure/globalLowest listed price: $5Lowest listed price: $25Source09/23/2026
AzureVia OpenRouterazure/us$5.5$27.5Source09/23/2026
Claude Platform on AWSVia OpenRouterclaude-on-awsLowest listed price: $5Lowest listed price: $25Source09/23/2026
GoogleVia OpenRoutergoogle-vertex/europe$5.5$27.5Source09/23/2026
GoogleVia OpenRoutergoogle-vertex/globalLowest listed price: $5Lowest listed price: $25Source09/23/2026
GoogleVia OpenRoutergoogle-vertex/us$5.5$27.5Source09/23/2026

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.

255075100CodingMathematicsFinanceLegalAgentic tasksProductivityHealthEducation
Claude Opus 5.5
Claude Opus 5
Coding: 100 / 76.1 (6 benchmark families)
Mathematics: 100 / 99 (1 benchmark family)
Finance: 97.9 / 99 (3 benchmark families)
Legal: 73.8 / 100 (2 benchmark families)
Agentic tasks: 100 / 96.6 (1 benchmark family)
Productivity: 91.8 / 100 (1 benchmark family)
Health: 89.2 / 99.8 (2 benchmark families)
Education: 92.7 / 100 (1 benchmark family)

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

Claude Opus 5.5Claude Opus 5
BioMysteryBenchOverall. Higher is better. No documented setup difference
Claude Opus 5.5Tie79.259 %
Claude Opus 5Tie79.259 %
Code MigrationOverall. Higher is better. No documented setup difference
Claude Opus 5.5Winner66.646 %
Claude Opus 557.473 %
EMBOverall. Higher is better. No documented setup difference
Claude Opus 5.5Winner75.938 %
Claude Opus 573.556 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
Claude Opus 5.558.587 %
Claude Opus 5Winner58.633 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
Claude Opus 5.53.75 %
Claude Opus 5Winner6.667 %
IOIOverall. Higher is better. No documented setup difference
Claude Opus 5.5Winner95.056 %
Claude Opus 584.333 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
Claude Opus 5.550.481 %
Claude Opus 5Winner55.288 %
MedCodeOverall. Higher is better. No documented setup difference
Claude Opus 5.549.797 %
Claude Opus 5Winner63.57 %
MedScribeOverall. Higher is better. No documented setup difference
Claude Opus 5.5Winner91.43 %
Claude Opus 590.985 %
MysteryMechanismOverall. Higher is better. No documented setup difference
Claude Opus 5.5Winner49.55 %
Claude Opus 537.387 %
ProgramBenchOverall. Higher is better. No documented setup difference
Claude Opus 5.5Winner18.5 %
Claude Opus 53 %
ProofBenchOverall. Higher is better. No documented setup difference
Claude Opus 5.5Winner100 %
Claude Opus 599 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Opus 5.5 and Claude Opus 5
Benchmark and taskClaude Opus 5.5Claude Opus 5Source
BioMysteryBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Harness: Terminus 2
Tie79.259 %
Tie79.259 %
Vals AI
Source details
Data as of: 09/22/2026
Code MigrationOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner66.646 %
57.473 %
Vals AI
Source details
Data as of: 09/22/2026
EMBOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner75.938 %
73.556 %
Vals AI
Source details
Data as of: 09/22/2026
Finance Agent (v2)Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better
58.587 %
Winner58.633 %
Vals AI
Source details
Data as of: 09/22/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved
Test details
No documented difference in the test setupVersion: 1Metric: task resolution rateScoring: Higher is better
3.75 %
Winner6.667 %
Vals AI
Source details
Data as of: 09/22/2026
IOIOverall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better
Winner95.056 %
84.333 %
Vals AI
Source details
Data as of: 09/22/2026
Legal Research BenchOverall · All-pass
Test details
No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is better
50.481 %
Winner55.288 %
Vals AI
Source details
Data as of: 09/22/2026
MedCodeOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
49.797 %
Winner63.57 %
Vals AI
Source details
Data as of: 09/22/2026
MedScribeOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner91.43 %
90.985 %
Vals AI
Source details
Data as of: 09/22/2026
MysteryMechanismOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner49.55 %
37.387 %
Vals AI
Source details
Data as of: 09/22/2026
ProgramBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner18.5 %
3 %
Vals AI
Source details
Data as of: 09/22/2026
ProofBenchOverall
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is better
Winner100 %
99 %
Vals AI
Source details
Data as of: 09/22/2026
Public Benefits Bench v1.1Overall
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is better
70.636 %
Winner76.928 %
Vals AI
Source details
Data as of: 09/22/2026
SAGEOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
45.831 %
Winner49.426 %
Vals AI
Source details
Data as of: 09/22/2026
SRE BenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner33.588 %
12.214 %
Vals AI
Source details
Data as of: 09/21/2026
Tax Agent BenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
70.499 %
Winner75.06 %
Vals AI
Source details
Data as of: 09/22/2026
Terminal-Bench 2.1Overall
Test details
No documented difference in the test setupVersion: 2.1Metric: accuracyScoring: Higher is better
Winner87.64 %
84.644 %
Vals AI
Source details
Data as of: 09/22/2026
Terminal-Bench 4.0Overall
Test details
No documented difference in the test setupVersion: 4.0Metric: accuracyScoring: Higher is better
Winner61.616 %
45.455 %
Vals AI
Source details
Data as of: 09/22/2026
Terminal-Bench ScienceOverall
Test details
No documented difference in the test setupVersion: 0.1Metric: accuracyScoring: Higher is better
Winner48.571 %
22.857 %
Vals AI
Source details
Data as of: 09/22/2026
Vals IndexOverall
Test details
No documented difference in the test setupVersion: 2Metric: weighted index scoreScoring: Higher is better
Winner69.689 %
67.213 %
Vals AI
Source details
Data as of: 09/22/2026
Vibe Code Bench 1-100Overall
Test details
No documented difference in the test setupVersion: 1.0Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands
Winner30.361 %
28.533 %
Vals AI
Source details
Data as of: 09/22/2026
Vibe Code Bench v1.1Overall
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands
Winner90.294 %
88.404 %
Vals AI
Source details
Data as of: 09/22/2026

Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Our tests

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.

Claude Opus 5.5

Not tested yet

Claude Opus 5

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

Reasoning (requested): high

First attempt
Run date
7 Sept 2026
API provider
openrouter
Requested API model
anthropic/claude-opus-5
Reasoning setting
high
Pinned endpoint
Anthropic | anthropic/claude-opus-5-20260723
Temperature
Provider default
Token limit including reasoning
8,192 tokens
Test protocol
community-visual-tests-v1
Technical checks
Failed

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

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

Related LLM comparisons

Compare Claude Opus 5.5 and Claude Opus 5 with other leading models using the same data and benchmark logic.

View the complete LLM comparison