Anthropic

Claude Opus 4.6

by Anthropictext+image+file->text6 endpoints
Neura Intelligence Index
80.2/ 100
Rank
#32
Confidence
high
Benchmarks
12(31% coverage)

Overview

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...

Capabilities

Text generation
Image understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
File input
Top-P sampling
Stop sequences

Modalities

Input
TextImageFile
Output
Text

Technical Specifications

Context Window
1M tokens
Max Output
128K tokens
Tokenizer
Claude
Content Moderation
Enabled
Uptime (24h)
10000.0%
Country
🇺🇸US
Release Date
February 5, 20267mo

Supported Parameters

include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_pverbosity

Benchmark Performance

general

BenchmarkScoreSource
MMMLU
91.1
verified
MRCR v2
76
verified

coding

BenchmarkScoreSource
SWE-bench Verified
80.8
verified

math

BenchmarkScoreSource
AIME 2025
99.8
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
91.3
verified
ARC-AGI v2
68.8
verified
Humanity's Last Exam
53.1
verified

multimodal

BenchmarkScoreSource
CharXiv Reasoning
77.4
verified
MMMU-Pro
77.3
verified

agent

BenchmarkScoreSource
BrowseComp
84
verified
OSWorld
72.7
verified
MCP Atlas
62.7
verified

Performance Over Time

Pricing

Per 1M tokens
Input$5.00
Output$25.00
Cache read$0.50
Cache write$6.25
Added
February 4, 2026
Last synced 9/18/2026