Claude Sonnet 4.6 (batch)
by Anthropictext+image+file->text1 endpoint
Neura Intelligence Index
59.0/ 100
Rank
#155—
Confidence
mediumBenchmarks
7(18% coverage)
Overview
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.
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
Country
🇺🇸US
Release Date
May 22, 20251y
Supported Parameters
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_pverbosity
Benchmark Performance
general
| Benchmark | Score | Source |
|---|---|---|
| MMMLU | 86.5 | verified |
coding
| Benchmark | Score | Source |
|---|---|---|
| SWE-bench Verified | 72.7 | verified |
| TerminalBench | 35.5 | verified |
math
| Benchmark | Score | Source |
|---|---|---|
| AIME 2025 | 70.5 | verified |
reasoning
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 75.4 | verified |
multimodal
| Benchmark | Score | Source |
|---|---|---|
| MMMU | 74.4 | verified |
agent
| Benchmark | Score | Source |
|---|---|---|
| TAU-Bench Retail | 80.5 | verified |
Performance Over Time
Pricing
Per 1M tokens
Input$1.50
Output$7.50
Cache read$0.15
Cache write$1.88
Added
February 17, 2026
Last synced 11/6/2026