Gemma 4 31B (Non-reasoning)
Gemma 4 31B (Non-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 #196 across 526
24.8
Coding
Rank #104 across 436
33.9
Blended Price
Rank #78 across 357
$0.205/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
Output Speed54.9 tok/s
First Token0.85s
Max Outputn/a
Pricing
Blended$0.205/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 24.8 | #196 |
| Artificial Analysis Coding Index | coding | 33.9 | #104 |
| GPQA | reasoning | 76.3% | #160 |
| Humanity's Last Exam | reasoning | 11.5% | #147 |
| SciCode |