Gemma 4 31B (Reasoning)
Gemma 4 31B (Reasoning) 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 Speed34.8 tok/s
First Token1.07s
Blended Price-
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseApr 2, 2026
Context Windown/a
Modalitiesn/a
Strength: GPQA
Rank #46 across 478 models.
85.7%
Strength: SciCode
Rank #52 across 472 models.
43.4%
Strength: HLE
Rank #55 across 474 models.
22.7%
Watch Area: Speed
Rank #266 across 293 models.
34.8 tok/s
Strength Profile
Percentile score by analysis domain.
Benchmark Percentiles
Higher bars mean stronger relative placement.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 39.2 | #77 |
| Artificial Analysis Coding Index | coding | 38.7 | #53 |
| GPQA | reasoning | 85.7% | #46 |
| Humanity's Last Exam | reasoning | 22.7% | #55 |
| SciCode |