TAU2
Measured May 14, 2026Source
Score
0.66
Gemma 4 31B (Non-reasoning) is a 31-billion parameter open model from Google, optimized for general-purpose tasks and fast inference. It is part of the Gemma family, derived from Gemini technology, and is designed for efficient performance in coding, instruction following, and multimodal understanding without the overhead of extended reasoning chains.
Benchmark history
Score
0.66
Score
0.3
Score
0.36
Score
0.53
Score
0.41
Score
0.12
Score
0.76
Score
33.9
Score
32.3
Plan availability

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