Back to Models
anthropic logo
anthropic/claude-opus-4
Not Available

Claude Opus 4

Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in software engineering, achieving leading results on SWE-bench (72.5%) and Terminal-bench (43.2%). Opus 4 supports extended, agentic workflows, handling thousands of task steps continuously for hours without degradation. Read more at the [blog post here](https://www.anthropic.com/news/claude-4)

5/22/2025
200,000 tokens
#76 Text (Creative Writing)

Specifications

Modalities

Input
image
text
file
Output
text

Supported Parameters

include_reasoning
max_tokens
reasoning
stop
temperature
tool_choice
tools
top_k
top_p

Max Output Tokens

32,000

Frequently asked questions

Is Claude Opus 4 available on FastMetal?
Not at the moment. Claude Sonnet 5, from the same lab, is available on the FastMetal API today.
What is the context window of Claude Opus 4?
200,000 tokens, shared between the prompt and the response.
How does Claude Opus 4 rank?
#89 on the public arena's Japanese board (ELO 1,382). Ranks move as the leaderboard is updated.

Leaderboard

Text
OverallELO: 1,414
#129
JapaneseELO: 1,382
#89
ChineseELO: 1,442
#128
KoreanELO: 1,362
#106
EnglishELO: 1,425
#129
frenchELO: 1,420
#130
germanELO: 1,430
#83
spanishELO: 1,403
#124
russianELO: 1,424
#99
CodingELO: 1,465
#117
MathELO: 1,404
#138
Creative WritingELO: 1,416
#76
Instruction FollowingELO: 1,415
#111
Hard PromptsELO: 1,436
#123
Multi-TurnELO: 1,431
#104
Vision
OverallELO: 1,189
#80
Code
OverallELO: 1,389
#80