ModelBeat
Models/Claude Opus 5
All models
A

Anthropic: Claude Opus 5

Watch this modelCompareAnnouncement
anthropic/claude-opus-5

Claude Opus 5 is Anthropic’s proprietary AI model, released Jul 24, 2026. It scores 164 on the Epoch Capabilities Index, costs $5/M input and $25/M output tokens, and handles a 1M-token context window. Its strongest use case is reasoning & knowledge, where it ranks in the 90th percentile of the models Model Beat tracks.

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.

Context
1M
Input
$5 / 1M
Output
$25 / 1M
Released
Jul 24, 2026
Modalities
textimagefile→text
Strongest atReasoning & Knowledge top 10%Coding top 11%Agentic & Tools top 11%

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where Claude Opus 5 lands among all models tracked on Model Beat.

86.0
Intelligence Index
Epoch AI
86th percentile of tracked models
89.0
Coding Index
Epoch AI
89th percentile of tracked models
89.0
Agentic Index
Epoch AI
89th percentile of tracked models

Reasoning

7 evals
ARC-AGI97.5%

Abstract visual reasoning

ARC-AGI-290.4%

Harder abstract reasoning

GPQA Diamond93.9%

Graduate-level scientific reasoning

Humanity's Last Exam54.9%

Frontier of human expert knowledge

SimpleBench80.6%

Common-sense trick questions

SimpleQA Verified59.9%

Factual accuracy & hallucination

WeirdML91.8%

Novel ML problem-solving

Coding

2 evals
SciCode56.4%

Scientific research coding

WebDev Arena1687

Human-rated web development

Math

1 evals
AIME 2024/202598.9%

Olympiad-qualifier math

Agentic & Tools

1 evals
APEX65.8%

Multi-step agentic tasks

In the news

22

Changelog

3
  • Claude Opus 5: reported APEX score rose from 43.5% to 65.8% (+51%)benchmark · Sep 22, 2026
  • Claude Opus 5: reported SimpleQA Verified score rose from 56.7% to 59.9% (+6%)benchmark · Aug 28, 2026
  • Claude Opus 5 added to the tracker: $5/$25 per 1M, 1M context.tracked · Jul 24, 2026

Compare Claude Opus 5 with

Claude Opus 5 vs GPT-6 AstraClaude Opus 5 vs Claude Opus 5.5Claude Opus 5 vs Gemini 3.7 FlashClaude Opus 5 vs Kimi K3Claude Opus 5 vs Grok 4.6

Frequently asked questions

What is Claude Opus 5?

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.

Who created Claude Opus 5?

Claude Opus 5 is an AI model developed by Anthropic, part of the Claude family, released Jul 24, 2026.

How much does Claude Opus 5 cost?

Claude Opus 5's list price from Anthropic is $5 per million input tokens and $25 per million output tokens.

What is Claude Opus 5's context window?

Claude Opus 5 supports a context window of up to 1M tokens.

How does Claude Opus 5 perform on benchmarks?

On standardized evaluations tracked by Epoch AI, Claude Opus 5 scores 54.9% on Humanity's Last Exam, 80.6% on SimpleBench, 91.8% on WeirdML.

Is Claude Opus 5 open source?

Claude Opus 5 is a proprietary model (API access), available through its provider's API rather than as a downloadable open-weight model.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Oct 29, 2026.