Claude Sonnet 4.6
Parameters
Undisclosed
Context Length
1M
Modality
Multimodal
Architecture
Undisclosed
License
Proprietary
Release Date
17 Feb 2026
Knowledge Cutoff
Aug 2025
API Pricing (per 1M)
Input: $1.50 · Output: $7.50
Evaluation Benchmarks
Rank
#53
| Benchmark | Score | Rank |
|---|---|---|
Graduate-Level QA | 0.899 | 25 |
Coding | medium 0.79 | 26 |
Data Analysis | medium 0.78 | 26 |
Reasoning | medium 0.85 | 37 |
Agent Arena | -1.52 | 41 |
General Text | 1472 | 42 |
General | medium 0.73 | 45 |
Mathematics | medium 0.87 | 45 |
LiveBench Average | medium 0.73 | 45 |
Web Development | 1523 | 47 |
Agentic Coding | medium 0.43 | 51 |
Agentic Index | max 0.32 | 56 |
Coding Index | max 0.63 | 63 |
Intelligence Index | max 0.30 high 0.25 low 0.23 | 102 137 150 |
Rankings
Overall Rank
#53
Coding Rank
#53
About Claude Sonnet 4.6
Claude Sonnet 4.6 is a high-performance multimodal workhorse from Anthropic optimized for agentic workflows, GUI navigation, and complex codebases. It features hybrid adaptive reasoning and context compaction across a 1M token context window.
Technical Specifications
Architecture specifications are undisclosed for proprietary models.
Resources
About Claude 4
Anthropic's fourth generation Claude models with advanced reasoning, extended context windows up to 200K tokens, and configurable thinking effort levels. Features improved safety alignment, nuanced understanding, and sophisticated task completion. Includes Opus (most capable), Sonnet (balanced), and Haiku (fast) variants, with thinking modes that enable transparent chain-of-thought reasoning for complex problems.