Gemma 4 31B by Google scores 69.2 out of 100 on the Neura Intelligence Index, ranking #71 among tracked AI models. This composite score is computed from 5 individual benchmarks across coding, math, reasoning, and language categories.

Gemma 4 31B costs $0.13/1M input tokens and $0.38/1M output tokens via API. At a typical 3:1 input-to-output ratio with 1M tokens/day usage, the estimated monthly cost is approximately $6.

Yes, Gemma 4 31B has open weights available under the apache_2_0 license. You can download and self-host the model.

Gemma 4 31B supports a context window of 262K tokens, allowing it to process very long documents, codebases, and conversations in a single request.

Gemma 4 31B achieves its highest score on MMMLU with a score of 88.4%. This benchmark evaluates multilingual massive multitask language understanding across many languages.