█

AI/TLDR

Buy me a coffee
Buy me a coffee

Model comparison

Claude Opus 4 vs Claude 3 Opus

Short answer

Claude Opus 4 scores higher on 3 of the 3 benchmarks both models report; both charge the same $15 per 1M input tokens.

Specs and pricing side by side

SpecClaude Opus 4Claude 3 Opus
MakerAnthropicAnthropicsame
Released2025-05-222024-03-04
Context window200K200Ksame
Max output32K4K
Input price$15.00$15.00same
Output price$75.00$75.00same
ParametersUndisclosed
LicenseProprietaryProprietarysame
WeightsAPI onlyAPI onlysame
ModalitiesText, VisionText, Visionsame
Knowledge cutoffnot publishedAugust 2023

Benchmarks both models report

BenchmarkClaude Opus 4Claude 3 Opus
GPQA Diamond74.9%50.4%
MMLU87.4%86.8%
MMMU73.7%59.4%

Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.

Which one should you pick?

Pick Claude Opus 4 if…

  • You care about GPQA Diamond, MMLU, MMMU (it scores higher on 3 shared benchmarks).
  • Your use case is: autonomous and agentic coding workflows.

Pick Claude 3 Opus if…

  • Your use case is: complex reasoning, analysis and long-document understanding over the 200K window.

FAQ

Which is better, Claude Opus 4 or Claude 3 Opus?

Claude Opus 4 scores higher on 3 of the 3 benchmarks both models report; both charge the same $15 per 1M input tokens. The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.

How do Claude Opus 4 and Claude 3 Opus pricing compare?

Claude Opus 4: $15.00 input, $75.00 output. Claude 3 Opus: $15.00 input, $75.00 output (list API prices as published by each maker).

What are the context windows of Claude Opus 4 and Claude 3 Opus?

Claude Opus 4 offers 200K with up to 32K output; Claude 3 Opus offers 200K with up to 4K output.

Is Claude Opus 4 newer than Claude 3 Opus?

Claude Opus 4 was released 2025-05-22; Claude 3 Opus was released 2024-03-04.

Go deeper