Gemma 3n E4B Instruct
Gemma 3n E4B 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 GemmaOperational Metrics
Output Speed15.3 tok/s
First Token0.34s
Blended Price$0.025/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseJun 26, 2025
Context Windown/a
Modalitiesn/a
Strength: Output $
Rank #1 across 325 models.
$0.040/M
Strength: Blended $
Rank #3 across 325 models.
$0.025/M
Strength: Input $
Rank #3 across 325 models.
$0.020/M
Watch Area: Speed
Rank #292 across 293 models.
15.3 tok/s
Watch Area: Overall
Rank #488 across 500 models.
6.4
Watch Area: GPQA
Rank #444 across 478 models.
29.6%
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.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 6.4 | #488 |
| Artificial Analysis Coding Index | coding | 4.2 | #371 |
| Artificial Analysis Math Index | math | 14.3 | #220 |
| MMLU-Pro | reasoning | 48.8% | #297 |