Gemma 4 31B
GoogleOpenApache 2.0
Gemma 4 31B is a vision-language model from Google. It ranks 39 of 167 on LMArena’s overall vision board with 1276±6 from 40,219 votes. Its best category is Homework (#31 of 118). License: Apache 2.0.
Key figures
- Developer
- License
- Apache 2.0
- First seen (our snapshots)
- 2026-10-26
Who it suits
- Overall #39 of 167: upper half.
- Strongest category: Homework (#31 of 118).
- Open weights (Apache 2.0): you can self-host it.
Neighbours on the overall board
| # | Model | Score | Votes | License | Δ vs this model |
|---|---|---|---|---|---|
| 36 |  GPT-6 Astra (Max) OpenAI | 1280 | 4,012 | Proprietary | +4 |
| 37 |  Qwen3.7-Plus Alibaba | 1278 | 14,212 | Proprietary | +2 |
| 38 |  DeepSeek-V4.1-Flash-20260910 (Max) DeepSeek | 1278 | 4,100 | MIT | +2 |
| 39 | Gemma 4 31B Google | 1276 | 40,219 | Apache 2.0 | |
| 40 |  Dola Seed 2.0 Pro ByteDance | 1274 | 10,972 | Proprietary | -2 |
| 41 |  Claude Sonnet 5 (High) Anthropic | 1273 | 14,034 | Proprietary | -3 |
| 42 |  Mistral Large 4 Mistral | 1272 | 1,008 | Proprietary | -4 |
Alternatives · More from Google
| # | Model | Score | Votes | License |
|---|---|---|---|---|
| 7 | Gemini 3.8 Flash (High) Google | 1315 | 4,645 | Proprietary |
| 8 | Gemini 3.7 Flash (High) Google | 1314 | 5,369 | Proprietary |
| 13 | Gemini 3.5 Flash (High) Google | 1308 | 13,862 | Proprietary |
| 14 | Gemini 3.5 Flash (Medium) Google | 1306 | 14,061 | Proprietary |
| 16 | Gemini 3 Pro Google | 1305 | 13,623 | Proprietary |
Alternatives · Top open-weight models
| # | Model | Score | Votes | License |
|---|---|---|---|---|
| 24 |  GLM-5.3-Flash Z.ai | 1294 | 16,254 | MIT |
| 34 |  Kimi K2.6 Moonshot AI | 1282 | 16,368 | Modified MIT |
| 38 | DeepSeek-V4.1-Flash-20260910 (Max) DeepSeek | 1278 | 4,100 | MIT |
| 44 | Qwen3.8-27B Alibaba | 1269 | 7,614 | Apache 2.0 |
| 46 | Kimi K2.5 (Thinking) Moonshot AI | 1269 | 28,249 | Modified MIT |
How to read these scores
- If two scores differ by less than their ± intervals, the models are statistically close.
- Each category board is computed independently; do not compare scores across categories.
- Models with few votes move more; ranks of new entries may change.
FAQ
Where does Gemma 4 31B rank among vision models?
Overall rank 39 (1276); OCR rank 43 (1282); Diagrams rank 49 (1283); Homework rank 31 (1310); Captioning rank 17 (1218); Entity recognition rank 30 (1226); Creative writing rank 28 (1285); Humor rank 29 (1280); English rank 47 (1271); Chinese rank 38 (1326) (LMArena, data as of Oct 26, 2026).
How good is Gemma 4 31B at OCR?
Gemma 4 31B ranks 43 of 123 on LMArena’s OCR board with 1282 (28,054 votes).
Is Gemma 4 31B better with Chinese or English prompts?
Chinese board: #38 of 128 (1326); English board: #47 of 167 (1271). The boards are computed separately, so compare ranks rather than scores.
Is Gemma 4 31B open-weight?
LMArena lists its license as Apache 2.0, not proprietary; check the license text for commercial use.
How far is Gemma 4 31B from #1?
#1 overall is Claude Fable 5 (High) (1325); Gemma 4 31B has 1276, 49 points behind.
Sources
LMArena data published Oct 19, 2026.
Synced here Oct 26, 2026.
Price, context length and release date have no reliable public data here and are not shown; all figures come from snapshots, blanks are –.