DataLearner logo

Claude Opus 5vsClaude Opus 4.6

Across 4 shared benchmarks, Claude Opus 5 leads overall: Claude Opus 5 wins 4, Claude Opus 4.6 wins 0, with 0 ties and an average score difference of +100.73.

Anthropic
Claude Opus 5

Anthropic · 2026-07-24 · Reasoning model

Anthropic
Claude Opus 4.6

Anthropic · 2026-02-05 · Reasoning model

Claude Opus 54 wins(100%)(0%)0 winsClaude Opus 4.6

Benchmark scores

Grouped by capability, sorted by largest gap within each. 4 shared benchmarks.

Math and Reasoning

Claude Opus 5 2/2
BenchmarkClaude Opus 5Claude Opus 4.6Diff
FrontierMath Tier 4 v273.176 / 42Max (No Tools)26.8323 / 42Max (No Tools)+46.34
FrontierMath v285.615 / 58Max (No Tools)65.9618 / 58Max (No Tools)+19.65

Coding and Software Engineer

Claude Opus 5 1/1
BenchmarkClaude Opus 5Claude Opus 4.6Diff
WeirdML v286.344 / 52Normal (With Tools)65.9023 / 52Normal (With Tools)+20.44

Writing and Creative Capabilities

Claude Opus 5 1/1
BenchmarkClaude Opus 5Claude Opus 4.6Diff
Creative Writing2,1213 / 106Normal (No Tools)1,80419 / 106Normal (No Tools)+316.50

Specs

FieldClaude Opus 5Claude Opus 4.6
PublisherAnthropicAnthropic
Release date2026-07-242026-02-05
Model typeReasoning modelReasoning model
ArchitectureDenseDense
ParametersNot availableNot available
Context length1M1000K
Max output128K64K

API pricing

Prices use DataLearner records when available; missing fields are not inferred.

ItemClaude Opus 5Claude Opus 4.6
Text input$5 / 1M tokens$5 / 1M tokens
Text output$25 / 1M tokens$25 / 1M tokens
Cache read$0.5 / 1M tokens$0.5 / 1M tokens
Cache write$6.25 / 1M tokens$6.25 / 1M tokens

Summary

  • Claude Opus 5leads in:Math and Reasoning (2/2), Coding and Software Engineer (1/1), Writing and Creative Capabilities (1/1)

On average across the 4 shared benchmarks, Claude Opus 5 scores 100.73 higher.

Largest single-benchmark gap: Creative Writing — Claude Opus 5 2,121 vs Claude Opus 4.6 1,804 (+316.50).

Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.