Google model product
Gemma 2 27B IT is an instruction-tuned version of Google's state-of-the-art open language model. Built from the same research and technology as Gemini, it's optimized for dialogue applications through supervised fine-tuning, distillation from larger models, and RLHF. The model excels at text generation tasks including question answering, summarization, and reasoning.
Updated Aug 10, 2026. Default version: Gemma 2 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 2 27B.
| ARC-E | 0.9 | 1 | 8 | 100.0% | C | |
| Natural Questions | 0.3 | 1 | 7 | 100.0% | C | |
| BIG-Bench | 0.7 | 2 | 3 | 50.0% | C | |
| BoolQ | 0.8 | 2 | 10 | 88.9% | C | |
| TriviaQA | 0.8 | 2 | 18 | 94.1% | C | |
| PIQA | 0.8 | 3 | 11 | 80.0% | C | |
| Social IQa | 0.5 | 4 | 9 | 62.5% | C | |
| AGIEval | 0.6 | 5 | 10 | 55.6% | C | |
| Winogrande | 0.8 | 6 | 22 | 76.2% | C | |
| HellaSwag | 0.9 | 10 | 27 | 65.4% | C | |
| ARC-C | 0.7 | 19 | 34 | 45.5% | C | |
| MBPP | 0.6 | 32 | 37 | 13.9% | C | |
| GSM8k | 0.7 | 42 | 48 | 12.8% | C | |
| MATH | 0.4 | 65 | 71 | 8.6% | C | |
| HumanEval | 0.5 | 71 | 76 | 6.7% | C | |
| MMLU | 0.8 | 76 | 100 | 24.2% | C |
Preference and agent-evaluation signals from published Arena datasets.
| text style control | polish | 161 | 1350.4 | 58 | N/A | |
| text style control | japanese | 186 | 1228.9 | 1,808 | N/A | |
| text | polish | 188 | 1276.0 | 58 | N/A | |
| text | japanese | 191 | 1175.9 | 1,808 | N/A | |
| text style control | korean | 205 | 1237.4 | 1,440 | N/A | |
| text style control | french | 208 | 1311.6 | 793 | N/A | |
| text | korean | 209 | 1173.9 | 1,440 | N/A | |
| text | french | 214 | 1246.1 | 793 | N/A | |
| text style control | spanish | 214 | 1291.5 | 845 | N/A | |
| text style control | german | 219 | 1269.3 | 2,037 | N/A | |
| text | spanish | 222 | 1227.4 | 845 | N/A | |
| text style control | creative writing | 222 | 1292.5 | 11,429 | N/A | |
| text | german | 228 | 1208.9 | 2,037 | N/A | |
| text style control | industry writing and literature and language | 239 | 1297.0 | 20,390 | N/A | |
| text style control | industry entertainment and sports and media | 241 | 1273.1 | 12,280 | N/A | |
| text style control | russian | 243 | 1290.5 | 9,678 | N/A | |
| text style control | chinese | 246 | 1299.0 | 6,872 | N/A | |
| text | creative writing | 249 | 1241.0 | 11,429 | N/A | |
| text style control | industry legal and government | 255 | 1311.2 | 4,458 | N/A | |
| text | russian | 256 | 1233.1 | 9,678 | N/A | |
| text | industry writing and literature and language | 257 | 1248.7 | 20,390 | N/A | |
| text style control | industry medicine and healthcare | 257 | 1290.3 | 3,862 | N/A | |
| text style control | longer query | 257 | 1299.7 | 9,918 | N/A | |
| text style control | non english | 258 | 1273.9 | 34,471 | N/A | |
| text style control | multi turn | 259 | 1279.5 | 13,588 | N/A | |
| text | chinese | 260 | 1220.1 | 6,872 | N/A | |
| text style control | overall | 263 | 1289.2 | 75,754 | N/A | |
| text style control | industry mathematical | 263 | 1264.3 | 8,869 | N/A | |
| text style control | instruction following | 264 | 1270.6 | 29,545 | N/A | |
| text | industry entertainment and sports and media | 265 | 1213.0 | 12,280 | N/A | |
| text | industry legal and government | 265 | 1241.2 | 4,458 | N/A | |
| text | non english | 265 | 1216.8 | 34,471 | N/A | |
| text style control | exclude ties | 266 | 1210.9 | 47,955 | N/A | |
| text style control | industry life and physical and social science | 266 | 1304.0 | 12,863 | N/A | |
| text style control | industry software and it services | 266 | 1310.1 | 19,950 | N/A | |
| text | industry mathematical | 267 | 1221.4 | 8,869 | N/A | |
| text | longer query | 267 | 1230.8 | 9,918 | N/A | |
| text style control | expert | 267 | 1257.3 | 4,025 | N/A | |
| text style control | industry business and management and financial operations | 267 | 1278.3 | 8,733 | N/A | |
| text | expert | 268 | 1170.7 | 4,025 | N/A | |
| text | multi turn | 268 | 1223.7 | 13,588 | N/A | |
| text | overall | 269 | 1231.6 | 75,754 | N/A | |
| text | exclude ties | 269 | 1129.2 | 47,955 | N/A | |
| text | industry medicine and healthcare | 269 | 1196.9 | 3,862 | N/A | |
| text style control | english | 269 | 1299.1 | 41,283 | N/A | |
| text style control | math | 269 | 1246.8 | 10,170 | N/A | |
| text | instruction following | 270 | 1206.4 | 29,545 | N/A | |
| text style control | hard prompts | 271 | 1282.0 | 20,494 | N/A | |
| text | industry business and management and financial operations | 273 | 1207.4 | 8,733 | N/A | |
| text | industry software and it services | 273 | 1228.9 | 19,950 | N/A | |
| text | math | 274 | 1212.0 | 10,170 | N/A | |
| text style control | hard prompts english | 274 | 1289.2 | 12,606 | N/A | |
| text | industry life and physical and social science | 275 | 1228.5 | 12,863 | N/A | |
| text | english | 276 | 1242.1 | 41,283 | N/A | |
| text | coding | 278 | 1211.4 | 12,088 | N/A | |
| text style control | coding | 278 | 1304.6 | 12,088 | N/A | |
| text | hard prompts | 280 | 1198.7 | 20,494 | N/A | |
| text | hard prompts english | 281 | 1207.6 | 12,606 | 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-2-27b-it | global | $0.65 | $0.65 | 8.2K |
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 2 27B | 47.1 | 27.2B | N/A | N/A | No | Gemma |
A concise description based on the published model registry.
Gemma 2 27B IT is an instruction-tuned version of Google's state-of-the-art open language model. Built from the same research and technology as Gemini, it's optimized for dialogue applications through supervised fine-tuning, distillation from larger models, and RLHF. The model excels at text generation tasks including question answering, summarization, and reasoning.
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 2 27B.
Gemma 2 27B's default version was released on Jun 27, 2024.
No official standard PAYG price is currently available for Gemma 2 27B. The lowest tracked third-party offer starts at $0.65 input and $0.65 output via OpenRouter.
Gemma 2 27B is published under Google in the model registry.
The current registry does not publish a context window for the default version.
No. The default version is not marked as having publicly available weights.
1 published provider offerings are linked to the default version.
Nearby ranked alternatives include Qwen3.6 35B A3B, Gemma 4 12B, Phi 4 Reasoning.