TAU2
Measured May 29, 2026Source
Score
0.94
Models9 2 
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)
AnthropicAnthropicUnited States
Anthropic is an AI research company that develops advanced language models such as Claude. Its Claude Opus 4.8 model features adaptive reasoning and is optimized for coding, agentic tasks, and long-context applications with a 1M token context window.
Input / 1M tokens
$6.25Output / 1M tokens
$25.00Output tokens/s
65.32First-token seconds
7.38sSupported plans
14Benchmark history
Evaluations
Terminalbench Hard
Measured May 29, 2026Source
Score
0.58
Lcr
Measured May 29, 2026Source
Score
0.68
Ifbench
Measured May 29, 2026Source
Score
0.62
Scicode
Measured May 29, 2026Source
Score
0.54
Hle
Measured May 29, 2026Source
Score
0.46
Gpqa
Measured May 29, 2026Source
Score
0.92
Artificial Analysis Coding Index
Measured May 29, 2026Source
Score
56.7
Artificial Analysis Intelligence Index
Measured May 29, 2026Source
Score
61.4
Plan availability
Products and plans that support this model
Claude Code
Claude Code
Claude Code is an AI coding agent by Anthropic that works in terminal, IDEs, and Slack to help developers build, debug, and ship code. It uses Claude models (Opus 4.8, Sonnet 4.6, Haiku 4.5) to understand codebases, make multi-file edits, and generate pull requests.
Cursor
Cursor
Cursor is an AI-powered coding agent and IDE that accelerates software development by providing intelligent code completion, agentic task execution, and integration with leading AI models for developers and teams.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server