Google model product
Gemma 3 27B is a 27-billion-parameter vision-language model from Google, handling text and image input and generating text output. It features a 128K context window, multilingual support, and open weights. Suitable for complex question answering, summarization, reasoning, and image understanding tasks.
Updated Aug 10, 2026. Default version: Gemma 3 27B
Structured fields from the published default version.
This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.
Published benchmark records for the scored version Gemma 3 27B.
| ECLeKTic | 0.2 | 2 | 8 | 85.7% | C | |
| HiddenMath | 0.6 | 2 | 13 | 91.7% | C | |
| VQAv2 (val) | 0.7 | 2 | 3 | 50.0% | C | |
| Bird-SQL (dev) | 0.5 | 3 | 7 | 66.7% | C | |
| Natural2Code | 0.8 | 3 | 8 | 71.4% | C | |
| BIG-Bench Hard | 0.9 | 4 | 21 | 85.0% | C | |
| Global-MMLU-Lite | 0.8 | 6 | 14 | 61.5% | C | |
| InfoVQA | 0.7 | 6 | 9 | 37.5% | C | |
| BIG-Bench Extra Hard | 0.2 | 7 | 11 | 40.0% | C | |
| FACTS Grounding | 0.7 | 7 | 13 | 50.0% | C | |
| MATH | 0.9 | 7 | 71 | 91.4% | C | |
| GSM8k | 1.0 | 8 | 48 | 85.1% | C | |
| MMMU (val) | 0.6 | 9 | 11 | 20.0% | C | |
| IFEval | 0.9 | 13 | 65 | 81.3% | C | |
| TextVQA | 0.7 | 14 | 15 | 7.1% | C | |
| WMT24++ | 0.5 | 14 | 23 | 40.9% | C | |
| MBPP | 0.7 | 19 | 37 | 50.0% | C | |
| ChartQA | 0.8 | 21 | 24 | 13.0% | C | |
| MathVista-Mini | 0.7 | 21 | 23 | 9.1% | C | |
| MRCR v2 (8-needle) | 0.1 | 21 | 21 | 0.0% | C | |
| AI2D | 0.8 | 23 | 32 | 29.0% | C | |
| DocVQA | 0.9 | 23 | 26 | 12.0% | C | |
| HumanEval | 0.9 | 30 | 76 | 61.3% | C | |
| SimpleQA | 0.1 | 41 | 46 | 11.1% | C | |
| LiveCodeBench | 0.3 | 62 | 73 | 15.3% | C | |
| MMLU-Pro | 0.7 | 92 | 129 | 28.9% | C | |
| GPQA | 0.4 | 197 | 233 | 15.5% | C |
Preference and agent-evaluation signals from published Arena datasets.
| vision | creative writing | 25 | 1182.1 | 732 | N/A | |
| vision style control | creative writing | 25 | 1174.6 | 732 | N/A | |
| vision | captioning | 27 | 1150.9 | 261 | N/A | |
| vision style control | captioning | 29 | 1117.8 | 261 | N/A | |
| vision | entity recognition | 34 | 1200.4 | 321 | N/A | |
| vision style control | entity recognition | 37 | 1174.7 | 321 | N/A | |
| vision style control | humor | 65 | 1152.4 | 770 | N/A | |
| vision | humor | 66 | 1165.9 | 770 | N/A | |
| vision | creative writing vision | 72 | 1184.3 | 626 | N/A | |
| vision style control | creative writing vision | 72 | 1174.0 | 626 | N/A | |
| vision | chinese | 73 | 1154.1 | 728 | N/A | |
| vision style control | chinese | 74 | 1169.0 | 728 | N/A | |
| vision style control | homework | 82 | 1171.8 | 1,050 | N/A | |
| vision | homework | 84 | 1164.8 | 1,050 | N/A | |
| vision | english | 85 | 1186.2 | 8,272 | N/A | |
| vision | diagram | 87 | 1157.6 | 1,743 | N/A | |
| vision style control | ocr | 88 | 1162.4 | 6,278 | N/A | |
| vision | ocr | 89 | 1158.6 | 6,278 | N/A | |
| vision style control | english | 90 | 1171.1 | 8,272 | N/A | |
| vision | overall | 91 | 1165.3 | 17,179 | N/A | |
| vision style control | overall | 91 | 1159.7 | 17,179 | N/A | |
| vision style control | diagram | 91 | 1166.5 | 1,743 | N/A | |
| text factuality | non english | 136 | 1369.3 | 973 | N/A | |
| text factuality | exclude ties | 137 | 1356.4 | 1,662 | N/A | |
| text factuality | overall | 138 | 1381.7 | 2,389 | N/A | |
| text | german | 139 | 1362.8 | 1,164 | N/A | |
| text factuality | hard prompts | 139 | 1392.7 | 1,045 | N/A | |
| text style control | japanese | 140 | 1309.4 | 951 | N/A | |
| text | japanese | 141 | 1286.8 | 951 | N/A | |
| text style control | german | 141 | 1371.3 | 1,164 | N/A | |
| text | korean | 143 | 1308.3 | 865 | N/A | |
| text style control | polish | 144 | 1368.0 | 2,795 | N/A | |
| text | industry medicine and healthcare | 145 | 1390.1 | 2,361 | N/A | |
| text style control | korean | 145 | 1324.9 | 865 | N/A | |
| text | creative writing | 148 | 1344.5 | 6,376 | N/A | |
| text | french | 148 | 1369.4 | 596 | N/A | |
| text | industry life and physical and social science | 151 | 1383.1 | 7,927 | N/A | |
| text | industry legal and government | 153 | 1374.6 | 2,714 | N/A | |
| text | polish | 153 | 1344.3 | 2,795 | N/A | |
| text | industry business and management and financial operations | 154 | 1359.6 | 6,578 | N/A | |
| text style control | french | 155 | 1387.7 | 596 | N/A | |
| text style control | industry medicine and healthcare | 155 | 1403.5 | 2,361 | N/A | |
| text style control | creative writing | 156 | 1347.5 | 6,376 | N/A | |
| text | industry writing and literature and language | 159 | 1347.0 | 10,671 | N/A | |
| text style control | russian | 159 | 1368.4 | 2,979 | N/A | |
| text style control | industry business and management and financial operations | 162 | 1376.8 | 6,578 | N/A | |
| text | russian | 164 | 1349.3 | 2,979 | N/A | |
| text | spanish | 165 | 1342.1 | 775 | N/A | |
| text style control | industry life and physical and social science | 165 | 1390.6 | 7,927 | N/A | |
| text style control | industry writing and literature and language | 166 | 1354.3 | 10,671 | N/A | |
| text style control | industry legal and government | 168 | 1382.0 | 2,714 | N/A | |
| text | industry entertainment and sports and media | 170 | 1320.8 | 8,078 | N/A | |
| text | overall | 171 | 1358.3 | 47,453 | N/A | |
| text | exclude ties | 171 | 1322.3 | 33,294 | N/A | |
| text style control | non english | 171 | 1353.1 | 22,650 | N/A | |
| text | english | 172 | 1374.3 | 24,793 | N/A | |
| text style control | spanish | 172 | 1350.0 | 775 | N/A | |
| text | non english | 173 | 1337.0 | 22,650 | N/A | |
| text style control | exclude ties | 174 | 1331.9 | 33,294 | N/A | |
| text style control | industry entertainment and sports and media | 174 | 1327.7 | 8,078 | N/A | |
| text style control | overall | 175 | 1365.8 | 47,453 | N/A | |
| text style control | multi turn | 178 | 1358.2 | 7,019 | N/A | |
| text | multi turn | 179 | 1345.2 | 7,019 | N/A | |
| text style control | longer query | 182 | 1363.8 | 6,626 | N/A | |
| text | instruction following | 183 | 1321.6 | 12,508 | N/A | |
| text | longer query | 184 | 1333.0 | 6,626 | N/A | |
| text style control | english | 184 | 1373.9 | 24,793 | N/A | |
| text style control | instruction following | 185 | 1343.8 | 12,508 | N/A | |
| text style control | chinese | 186 | 1373.1 | 2,286 | N/A | |
| text | chinese | 187 | 1346.6 | 2,286 | N/A | |
| text | hard prompts | 189 | 1339.9 | 17,840 | N/A | |
| text | industry software and it services | 192 | 1355.9 | 14,415 | N/A | |
| text style control | hard prompts | 192 | 1365.6 | 17,840 | N/A | |
| text | hard prompts english | 193 | 1349.5 | 9,896 | N/A | |
| text | industry mathematical | 194 | 1326.9 | 3,189 | N/A | |
| text style control | industry mathematical | 195 | 1340.1 | 3,189 | N/A | |
| text | expert | 198 | 1302.4 | 2,221 | N/A | |
| text style control | hard prompts english | 199 | 1370.3 | 9,896 | N/A | |
| text style control | industry software and it services | 200 | 1377.9 | 14,415 | N/A | |
| text | math | 201 | 1311.4 | 3,576 | N/A | |
| text style control | expert | 201 | 1335.1 | 2,221 | N/A | |
| text style control | math | 201 | 1322.3 | 3,576 | N/A | |
| text | coding | 208 | 1322.7 | 8,067 | N/A | |
| text style control | coding | 230 | 1358.0 | 8,067 | N/A |
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
| OpenRouter | google/gemma-3-27b-it | global | $0.08 | $0.45 | 262.1K | |
| Cortecs | gemma-3-27b-it | global | $0.099 | $0.299 | 131K | |
| LLM Gateway | gemma-3-27b | global | $0.10 | $0.30 | 110K | |
| NovitaAI | google/gemma-3-27b-it | global | $0.119 | $0.20 | 98.3K | |
| GreenPT | gemma-3-27b-it | global | $0.342 | $0.684 | 40K | |
| STACKIT | google/gemma-3-27b-it | global | $0.53 | $0.76 | 37K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.
| Gemma 3 27B | 45.1 | 27B | 131.1K | 131.1K | No | Gemma |
A concise description based on the published model registry.
Gemma 3 27B is a 27-billion-parameter vision-language model from Google, handling text and image input and generating text output. It features a 128K context window, multilingual support, and open weights. Suitable for complex question answering, summarization, reasoning, and image understanding tasks.
Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.
Data snapshot: 2026-08-07. Editorial model content is not available in the backend.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest published LLMBoard score.
Common questions about Gemma 3 27B.
Gemma 3 27B's default version was released on Mar 12, 2025.
No official standard PAYG price is currently available for Gemma 3 27B. The lowest tracked third-party offer starts at $0.08 input and $0.45 output via OpenRouter.
Gemma 3 27B is published under Google in the model registry.
The default version has a 131.1K token context window.
No. The default version is not marked as having publicly available weights.
6 published provider offerings are linked to the default version.
Nearby ranked alternatives include Gemma 2 27B, Sarvam 30B, Qwen2.5 Coder 32B.