Claude Opus 4.6
Parameters
Undisclosed
Context Length
1M
Modality
Multimodal
Architecture
Undisclosed
License
Proprietary
Release Date
5 Feb 2026
Knowledge Cutoff
Aug 2025
API Pricing (per 1M)
Input: $5.00 · Output: $25.00
Evaluation Benchmarks
Rank
#18
| Benchmark | Score | Rank |
|---|---|---|
General Text | 1498 | 6 |
Software Engineering | 0.76 | 7 |
Agent Arena | 0.05 | 14 |
Reasoning | high 0.89 | 15 |
Graduate-Level QA | 0.913 | 16 |
Coding | high 0.78 | 22 |
Web Development | high 1546 Standard 1537 | 23 27 |
Mathematics | high 0.89 | 25 |
General | high 0.75 | 26 |
LiveBench Average | high 0.75 | 26 |
Agentic Coding | high 0.49 | 28 |
Data Analysis | high 0.70 | 32 |
Intelligence Index | max 0.32 high 0.26 | 62 84 |
Rankings
Overall Rank
#18
Coding Rank
#18
About Claude Opus 4.6
Claude Opus 4.6 is Anthropic's flagship intelligence model engineered for high-stakes enterprise reasoning and autonomous software development. It supports adaptive thinking levels and a 1M token context window with up to 128K generation capacity.
Technical Specifications
Architecture specifications are undisclosed for proprietary models.
Attention
Attention Structure
Multi-Head Attention
Attention Heads
Undisclosed
Key-Value Heads
Undisclosed
Attention Head Dimension
Undisclosed
Position Embedding
Absolute Position Embedding
RoPE Theta
Undisclosed
Sliding Window Attention
Undisclosed
Sliding Window Size
Undisclosed
Sliding Window Ratio
Undisclosed
Linear Attention
Undisclosed
Linear Attention Ratio
Undisclosed
Normalization
RMS Normalization
Activation Function
Undisclosed
Dimensions
Hidden Dimension Size
Undisclosed
Number of Layers
Undisclosed
FFN Intermediate Size (Dense)
Undisclosed
Multi-Token Prediction Heads
Undisclosed
Tokenizer
Vocabulary Size
Undisclosed
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.