Claude Opus 4.1

by Anthropic

Claude Opus 4.1 builds on Opus 4 with notable improvements in agentic tasks, real-world coding, and research. It scores 74.5% on SWE-bench Verified, advancing state-of-the-art coding performance, with particularly strong gains in multi-file code refactoring. The upgrade sharpens in-depth research and data analysis, especially detail tracking and agentic search, making it more effective for complex investigative workflows and multi-step reasoning. On a third-party junior developer benchmark, Windsurf measured a leap from Opus 4 comparable to the jump from Sonnet 3.7 to Sonnet 4. With a 200K token context window and support for vision, tools, and structured output, Opus 4.1 strengthens professional coding, research, and knowledge work.

Key info

Input
Output
Features
Context window
200K
Max output
32K

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Intelligence Index22.8
Math Index80.3
Reasoning & knowledge
MMLU-Pro
88%
GPQA Diamond
81%
Humanity's Last Exam
13%
Long-context reasoning
76%
Coding
LiveCodeBench
65%
Agentic & tool use
Terminal-Bench Hard
34%
τ²-Bench Telecom
71%
Math & instruction following
AIME 2025
80%
IFBench
55%

Available routes

No routes currently available — Claude Opus 4.1 isn't routed through the Opper gateway right now. It may return.

Contact us about this model →

Available models from Anthropic

Start building with 700+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation