TAU2
Measured May 14, 2026Source
Score
0.85
Models9 2 
Claude Opus 4.6 (Non-reasoning, High Effort)
AnthropicAnthropicUnited States
Claude Opus 4.6 is a high-capability, high-compute model from Anthropic's Claude family, optimized for tasks requiring high effort and quality. It is designed to deliver strong performance in complex generation and analysis tasks, particularly excelling in coding and long-context understanding.
CodingLong context
Input / 1M tokens
$6.25Output / 1M tokens
$25.00Output tokens/s
46.92First-token seconds
1.62sSupported plans
10Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.48
Lcr
Measured May 14, 2026Source
Score
0.58
Ifbench
Measured May 14, 2026Source
Score
0.45
Scicode
Measured May 14, 2026Source
Score
0.46
Hle
Measured May 14, 2026Source
Score
0.19
Gpqa
Measured May 14, 2026Source
Score
0.84
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
47.6
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
46.5
Plan availability
Products and plans that support this model
Apertis Coding Plan
Apertis Coding Plan
Apertis Coding Plan is a subscription-based AI coding service providing unified access to 30+ AI models (GPT-5.4, Claude Opus 4.6, Gemini 3.1 Pro, and more) through a single API key. Designed for developers using coding agents like Claude Code, Cursor, Cline, and OpenCode, it offers predictable monthly pricing, free prompt caching, auto-failover, and quota-based billing across OpenAI, Anthropic, Google, and other providers.
Command Code AI
Command Code AI
Command Code AI is a frontier AI coding agent that runs in the terminal and continuously learns your coding taste. It supports multiple premium and open-source models, providing code generation, bug fixing, testing, and refactoring with personalized style preferences. Starts at $1/month.
Discussion
Thinking... Make sure you are connected to GitHub server