Gemma 3 4B by Google scores 5.7 out of 100 on the Neura Intelligence Index, ranking #355 among tracked AI models. This composite score is computed from 2 individual benchmarks across coding, math, reasoning, and language categories.

Gemma 3 4B costs $0.05/1M input tokens and $0.1/1M output tokens via API. At a typical 3:1 input-to-output ratio with 1M tokens/day usage, the estimated monthly cost is approximately $2.

Yes, Gemma 3 4B has open weights available under the gemma license. You can download and self-host the model.

Gemma 3 4B supports a context window of 131K tokens, allowing it to process moderate-length documents and conversations in a single request.

Gemma 3 4B achieves its highest score on GPQA Diamond with a score of 30.8%. This benchmark evaluates 448 graduate-level science questions (biology, chemistry, physics) designed to be hard for non-experts.