TAU2
Measured Jul 10, 2026Source
Score
0.89
Models12 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
$5.00Output / 1M tokens
$25.00Output tokens/s
54.19First-token seconds
9.04sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured Jul 10, 2026Source
Score
0.47
Lcr
Measured Jul 10, 2026Source
Score
0.74
Ifbench
Measured Jul 10, 2026Source
Score
0.58
Aime 25
Measured Jul 10, 2026Source
Score
0.91
Scicode
Measured Jul 10, 2026Source
Score
0.5
Livecodebench
Measured Jul 10, 2026Source
Score
0.87
Hle
Measured Jul 10, 2026Source
Score
0.28
Gpqa
Measured Jul 10, 2026Source
Score
0.87
Mmlu Pro
Measured Jul 10, 2026Source
Score
0.9
Artificial Analysis Math Index
Measured Jul 10, 2026Source
Score
91.3
Artificial Analysis Intelligence Index
Measured Jul 10, 2026Source
Score
40.8
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server