LIVE
ANTHROPICOpus 4.7 benchmarks published2m ago
CLAUDEOK142ms
OPUS 4.7$15 / $75per Mtok
CHATGPTOK89ms
HACKERNEWSWhy has not AI improved design quality the way it improved dev speed?14m ago
MMLU-PROleader Opus 4.788.4
GEMINIDEGRADED312ms
MISTRALMistral Medium 3 released6m ago
GPT-4o$5 / $15per Mtok
ARXIVCompositional reasoning in LRMs22m ago
BEDROCKOK178ms
GEMINI 2.5$3.50 / $10.50per Mtok
THE VERGEFrontier Model Forum expansion announced38m ago
SWE-BENCHleader Claude Opus 4.772.1%
MISTRALOK104ms
ANTHROPICOpus 4.7 benchmarks published2m ago
CLAUDEOK142ms
OPUS 4.7$15 / $75per Mtok
CHATGPTOK89ms
HACKERNEWSWhy has not AI improved design quality the way it improved dev speed?14m ago
MMLU-PROleader Opus 4.788.4
GEMINIDEGRADED312ms
MISTRALMistral Medium 3 released6m ago
GPT-4o$5 / $15per Mtok
ARXIVCompositional reasoning in LRMs22m ago
BEDROCKOK178ms
GEMINI 2.5$3.50 / $10.50per Mtok
THE VERGEFrontier Model Forum expansion announced38m ago
SWE-BENCHleader Claude Opus 4.772.1%
MISTRALOK104ms

Claude Opus 4.6

Flagship

by Anthropic

Claude Opus 4.6 was Anthropic's flagship until April 17, 2026, when Opus 4.7 succeeded it with a 1 million token context window at the same price. 4.6 remains available on the API and still leads on many reasoning and code benchmarks. It ships with a 200K context window, full tool use, and vision, and is a solid choice for workloads that do not need the larger context.

Input Price

$15.00

per 1M tokens

Output Price

$75.00

per 1M tokens

Context Window

200K

tokens

Released

2026-03

API access

Capabilities

textvisiontool-usecode

Key Strengths

  • Previous-gen flagship, still strong
  • Top-tier reasoning
  • Best-in-class code generation
  • 200K context window

Best For

  • Complex analysis and research
  • Large codebase refactoring
  • Multi-step agent workflows
  • Long document processing

Benchmark Scores

BenchmarkScoreDescription
MMLU-Pro92.4General knowledge and reasoning across 57 subjects
HumanEval95.1Python code generation and problem solving
GPQA Diamond74.2Graduate-level science questions verified by domain experts
MATH91.8Competition-level mathematics problems
SWE-bench62.3Real-world software engineering tasks from GitHub issues

Scores sourced from public benchmark datasets. See full benchmark leaderboard for all models.

Pricing Details

Input tokens

$15.00

per 1M tokens

Output tokens

$75.00

per 1M tokens

Estimated cost per 1K requests

$52.50

~1K input + ~500 output tokens avg

Prices are subject to change. Check the official documentation for current pricing. See the cost calculator for detailed estimates.

Related Models

View DocumentationCompare ModelsCost CalculatorFull Pricing Guide