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 GemmaModel Snapshot
ReleaseApr 2, 2026
Overall
Rank #163 across 600
29.4
Coding
Rank #127 across 266
43.4
Blended Price
No rank
n/a
Strength Profile
Percentile score by analysis domain.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed35.4 tok/s
First Token0.95s
Max Outputn/a
Pricing
Blended-
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 29.4 | #163 |
| Artificial Analysis Coding Index | coding | 43.4 | #127 |
| GPQA | reasoning | 85.7% | #89 |
| Humanity's Last Exam | reasoning | 22.7% | #102 |
| SciCode |