TAU2
Measured May 14, 2026Source
Score
0.89
Models13 0 
Claude Opus 4.5 (Reasoning)
AnthropicAnthropicUnited States
Claude Opus 4.5 (Reasoning) is Anthropic's most capable model, optimized for deep reasoning and complex problem-solving. It features an advanced 'thinking' mode that allows for extended chain-of-thought processing to tackle intricate tasks in coding, analysis, and creative work.
ReasoningCodingMultimodal
Input / 1M tokens
$6.25Output / 1M tokens
$25.00Output tokens/s
63.99First-token seconds
11.64sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.47
Lcr
Measured May 14, 2026Source
Score
0.74
Ifbench
Measured May 14, 2026Source
Score
0.58
Aime 25
Measured May 14, 2026Source
Score
0.91
Scicode
Measured May 14, 2026Source
Score
0.5
Livecodebench
Measured May 14, 2026Source
Score
0.87
Hle
Measured May 14, 2026Source
Score
0.28
Gpqa
Measured May 14, 2026Source
Score
0.87
Mmlu Pro
Measured May 14, 2026Source
Score
0.9
Artificial Analysis Math Index
Measured May 14, 2026Source
Score
91.3
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
47.8
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
49.7
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
Discussion
Thinking... Make sure you are connected to GitHub server