Skip to main content

Head-to-head comparison

Claude Opus 5 vs. Claude Opus 4.8

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

shared result series
28
distinct benchmarks
28
latest retrieval
2026-09-29

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 Claude Opus 4.8
AttributeClaude Opus 5Claude Opus 4.8
ProviderAnthropicAnthropic
ReleasedJul 24, 2026May 2026
AvailabilityActiveLegacy
Model typeProprietaryProprietary
ParametersNot publishedNot published
ArchitectureNot publishedNot published
Context window1,000,000 tokens1,000,000 tokens
Knowledge cutoffMay 2026January 2026
Technical sourcesModel, Knowledge cutoffModel, 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 Claude Opus 4.8
Price typeClaude Opus 5Claude Opus 4.8
API input$5$5
API output$25$25
Cache read$0.5$0.5
Cache write (5 min.)$6.25$6.25
Cache write (1 hr.)$10$10
Price verified09/22/2026 Source09/22/2026 Source
Claude Opus 5Claude Opus 4.8
API inputUSD per 1M tokens, base tier
Claude Opus 5Tie$5
Claude Opus 4.8Tie$5
API outputUSD per 1M tokens, base tier
Claude Opus 5Tie$25
Claude Opus 4.8Tie$25
Cache readUSD per 1M tokens, base tier
Claude Opus 5Tie$0.5
Claude Opus 4.8Tie$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.

No provider tariff for Claude Opus 4.8 is available in the stored OpenRouter snapshot. The official direct price is still shown.

Provider pricing for Claude Opus 5 and Claude Opus 4.8
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
Claude Opus 5AnthropicDirect from developerStandard APILowest listed price: $5Lowest listed price: $25Source09/22/2026
Amazon BedrockVia OpenRouteramazon-bedrockLowest listed price: $5Lowest listed price: $25Source10/15/2026
Amazon BedrockVia OpenRouteramazon-bedrock/eu-west-1$5.5$27.5Source10/15/2026
Amazon BedrockVia OpenRouteramazon-bedrock/us-east-1$5.5$27.5Source10/15/2026
AnthropicVia OpenRouteranthropicLowest listed price: $5Lowest listed price: $25Source10/15/2026
AnthropicVia OpenRouteranthropic/fast$10$50Source10/15/2026
AzureVia OpenRouterazure/globalLowest listed price: $5Lowest listed price: $25Source10/15/2026
AzureVia OpenRouterazure/us$5.5$27.5Source10/15/2026
Claude Platform on AWSVia OpenRouterclaude-on-awsLowest listed price: $5Lowest listed price: $25Source10/15/2026
GoogleVia OpenRoutergoogle-vertex/europe$5.5$27.5Source10/15/2026
GoogleVia OpenRoutergoogle-vertex/globalLowest listed price: $5Lowest listed price: $25Source10/15/2026
GoogleVia OpenRoutergoogle-vertex/us$5.5$27.5Source10/15/2026
Claude Opus 4.8AnthropicDirect from developerStandard APILowest listed price: $5Lowest listed price: $25Source09/22/2026

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 tasksMultimodalProductivity
Claude Opus 5
Claude Opus 4.8
Coding: 100 / 72.4 (6 benchmark families)
Reasoning: 100 / 98.9 (1 benchmark family)
Knowledge: 100 / 97.8 (1 benchmark family)
Finance: 99.9 / 93.5 (6 benchmark families)
Legal: 89.9 / 91.7 (3 benchmark families)
Agentic tasks: 100 / 81.9 (3 benchmark families)
Multimodal: 100 / 96.3 (1 benchmark family)
Productivity: 100 / 88.6 (1 benchmark family)

28 matched rows from 27 benchmark families were considered. The radar shows 8 of 12 comparable categories.

Claude Opus 5Claude Opus 4.8
Code MigrationOverall. Higher is better. No documented setup difference
Claude Opus 5Winner57.473 %
Claude Opus 4.847.25 %
CorpFin v2Overall. Higher is better. No documented setup difference
Claude Opus 5Winner73.194 %
Claude Opus 4.866.706 %
EMBOverall. Higher is better. No documented setup difference
Claude Opus 5Winner73.556 %
Claude Opus 4.869.373 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
Claude Opus 5Winner58.633 %
Claude Opus 4.853.918 %
GPQA DiamondOverall. Higher is better. No documented setup difference
Claude Opus 5Winner93.434 %
Claude Opus 4.892.424 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
Claude Opus 56.667 %
Claude Opus 4.8Winner9.583 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
Claude Opus 5Winner55.288 %
Claude Opus 4.843.75 %
LegalBenchOverall. Higher is better. No documented setup difference
Claude Opus 5Winner86.974 %
Claude Opus 4.883.568 %
LiveCodeBench v6Overall. Higher is better. No documented setup difference
Claude Opus 5Winner89.033 %
Claude Opus 4.887.819 %
MedCodeOverall. Higher is better. No documented setup difference
Claude Opus 5Winner63.57 %
Claude Opus 4.853.217 %
MedScribeOverall. Higher is better. No documented setup difference
Claude Opus 5Winner90.985 %
Claude Opus 4.885.755 %
MMLU-ProOverall. Higher is better. No documented setup difference
Claude Opus 5Winner91.591 %
Claude Opus 4.889.585 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Opus 5 and Claude Opus 4.8
Benchmark and taskClaude Opus 5Claude Opus 4.8Source
Code MigrationOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner57.473 %
47.25 %
Vals AI
Source details
Data as of: 09/27/2026
CorpFin v2Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better
Winner73.194 %
66.706 %
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
Winner73.556 %
69.373 %
Vals AI
Source details
Data as of: 09/27/2026
Finance Agent (v2)Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better
Winner58.633 %
53.918 %
Vals AI
Source details
Data as of: 09/27/2026
GPQA DiamondOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner93.434 %
92.424 %
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
6.667 %
Winner9.583 %
Vals AI
Source details
Data as of: 09/27/2026
Legal Research BenchOverall · All-pass
Test details
No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is better
Winner55.288 %
43.75 %
Vals AI
Source details
Data as of: 09/27/2026
LegalBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner86.974 %
83.568 %
Vals AI
Source details
Data as of: 09/27/2026
LiveCodeBench v6Overall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner89.033 %
87.819 %
Vals AI
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 %
53.217 %
Vals AI
Source details
Data as of: 09/26/2026
MedScribeOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner90.985 %
85.755 %
Vals AI
Source details
Data as of: 09/26/2026
MMLU-ProOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner91.591 %
89.585 %
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 %
86.59 %
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 %
69.912 %
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 %
Vals AI
Source details
Data as of: 09/27/2026
Public Benefits Bench v1.1Overall
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is better
Winner76.928 %
68.133 %
Vals AI
Source details
Data as of: 09/27/2026
SAGEOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
49.426 %
Winner54.788 %
Vals AI
Source details
Data as of: 09/26/2026
SkillsBenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands
Winner60.441 %
59.227 %
Vals AI
Source details
Data as of: 09/27/2026
SWE-bench VerifiedOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner97 %
88.6 %
Vals AI
Source details
Data as of: 09/01/2026
Tax Agent BenchOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
Winner75.06 %
64.906 %
Vals AI
Source details
Data as of: 09/27/2026
TaxEval v2Overall
Test details
No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better
75.143 %
Winner75.634 %
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
Winner84.644 %
71.91 %
Vals AI
Source details
Data as of: 09/27/2026
Terminal-Bench 4.0Overall
Test details
No documented difference in the test setupVersion: 4.0Metric: accuracyScoring: Higher is better
Winner45.455 %
16.162 %
Vals AI
Source details
Data as of: 09/27/2026
Terminal-Bench ScienceOverall
Test details
No documented difference in the test setupVersion: 0.1Metric: accuracyScoring: Higher is better
Winner22.857 %
10 %
Vals AI
Source details
Data as of: 09/27/2026
Time Horizon Index: KSPOverall
Test details
No documented difference in the test setupVersion: 1Metric: progressScoring: Higher is better
Winner18.833 %
11.833 %
Vals AI
Source details
Data as of: 09/14/2026
Vals IndexOverall
Test details
No documented difference in the test setupVersion: 2Metric: weighted index scoreScoring: Higher is better
Winner67.213 %
60.908 %
Vals AI
Source details
Data as of: 09/27/2026
Vals Multimodal IndexOverall
Test details
No documented difference in the test setupVersion: 1.2Metric: weighted index scoreScoring: Higher is better
Winner73.896 %
70.889 %
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 %
82.725 %
Vals AI
Source details
Data as of: 09/27/2026

Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Our tests

SVG short test

One SVG prompt and fixed output settings. Captures are shown only with 0 reported reasoning tokens or documented lack of reasoning controls. Identical test conditions do not make the models' internal compute identical.

Shared test round: 4ae5d8eeb9a9

Claude Opus 5

Unavailable in this round

Claude Opus 4.8

Unavailable in this round

Earlier tests

Pelican on a bicycle

A community classic for free-form SVG drawing.

Claude Opus 5

Claude Opus 5: Pelican on a bicycle
A community classic for free-form SVG drawing.

Reasoning (requested): high

Current attempt
Run date
Oct 1, 2026
API provider
openrouter
Requested API model
anthropic/claude-opus-5
API model reported in response
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
Passed, not a quality rating
Response time
63 s

Visually reviewed. This individual test does not establish overall model quality.

Earlier attempts (1)
  • Sep 7, 2026API request failedReasoning setting: high

Claude Opus 4.8

Claude Opus 4.8: Pelican on a bicycle
A community classic for free-form SVG drawing.

Reasoning (requested): high

Current attempt
Run date
Oct 1, 2026
API provider
openrouter
Requested API model
anthropic/claude-opus-4.8
API model reported in response
anthropic/claude-opus-4.8
Reasoning setting
high
Pinned endpoint
Anthropic | anthropic/claude-4.8-opus-20260528
Temperature
Provider default
Token limit including reasoning
8,192 tokens
Test protocol
community-visual-tests-v1
Technical checks
Passed, not a quality rating
Response time
18 s

Visually reviewed. This individual test does not establish overall model quality.

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 and Claude Opus 4.8 with other leading models using the same data and benchmark logic.

View the complete LLM comparison