TAU2
Measured May 14, 2026Source
Score
0.74
This is a variant of the Claude Opus 4.7 model optimized for non-reasoning tasks. It is configured to operate in a 'High Effort' mode, likely dedicating more computational resources to generating high-quality, detailed, and nuanced outputs for tasks like writing, analysis, and creative work, rather than focusing on step-by-step logical reasoning.
Benchmark history
Score
0.74
Score
0.55
Score
0.67
Score
0.44
Score
0.5
Score
0.31
Score
0.89
Score
53.1
Score
51.8
Plan availability

Thinking... Make sure you are connected to GitHub server