Models

Gemma 4 31B (Non-reasoning)

GoogleGoogleUnited States

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.

CodingFastCheapMultimodal
Input / 1M tokens
$0.14
Output / 1M tokens
$0.40
Output tokens/s
61.48
First-token seconds
0.77s
Supported plans
0

Benchmark history

Evaluations

11

TAU2

Measured Jul 10, 2026Source

Score

0.66

Terminalbench Hard

Measured Jul 10, 2026Source

Score

0.3

Lcr

Measured Jul 10, 2026Source

Score

0.36

Ifbench

Measured Jul 10, 2026Source

Score

0.53

Scicode

Measured Jul 10, 2026Source

Score

0.41

Hle

Measured Jul 10, 2026Source

Score

0.12

Gpqa

Measured Jul 10, 2026Source

Score

0.76

Artificial Analysis Intelligence Index

Measured Jul 10, 2026Source

Score

24.8

Tau Banking

Measured Jul 10, 2026Source

Score

0.15

Terminalbench V2 1

Measured Jul 10, 2026Source

Score

0.43

Artificial Analysis Coding Index

Measured Jul 10, 2026Source

Score

43.4

Plan availability

Products and plans that support this model

0
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