Gemma 3 4B Instruct
Gemma 3 4B Instruct is a Google Gemma open-model profile, aimed at developers who want deployable Google-developed models rather than hosted Gemini-only access. The benchmark data is especially useful for comparing its efficiency and capability against similarly sized open and open-weight alternatives.
Introducing GemmaModel Snapshot
ReleaseMar 12, 2025
Overall
Rank #513 across 523
6.3
Coding
Rank #403 across 433
2.9
Blended Price
Rank #7 across 355
$0.050/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Max Outputn/a
Streaming speed is not measured for this model yet.
Pricing
Blended$0.050/M
Input$0.040/M
Output$0.080/M
Metadata
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 6.3 | #513 |
| Artificial Analysis Coding Index | coding | 2.9 | #403 |
| Artificial Analysis Math Index | math | 12.7 | #228 |
| MMLU-Pro | reasoning | 41.7% | #315 |