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 GemmaRank #202 across 566
Rank #132 across 222
Rank #62 across 371
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 21.8 | #202 |
| Artificial Analysis Coding Index | coding | 33.2 | #132 |
| GPQA | reasoning | 76.3% | #190 |
| Humanity's Last Exam | reasoning | 11.5% | #178 |
| SciCode |
| coding, reasoning |
| 41.1% |
| #114 |
| Output Speed | speed | 43.7 tok/s | #285 |
| Time to First Token | speed | 0.83s | #110 |
| Blended Price | cost | $0.205/M | #62 |
| Input Price | cost | $0.140/M | #56 |
| Output Price | cost | $0.400/M | #48 |
| Value Index | cost, overall | 106.3 | #27 |