llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsGemma 2 27B

Google model product

Gemma 2 27B

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

Compare
LLMBoard score47.1Gemma 2 27B
Coverage100%12 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
Gemma 2 27B
Released
Jun 27, 2024
Knowledge cutoff
Unknown
Parameters
27.2B
Context window
N/A
Max output
N/A
Inputs
text
Outputs
text
Open weights
No
License
Gemma

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

Gemma 2 27B category scores

Benchmark results

Published benchmark records for the scored version Gemma 2 27B.

16 rows
Columns

Show columns

ARC-E0.918100.0%CAug 7, 2026
Natural Questions0.317100.0%CAug 7, 2026
BIG-Bench0.72350.0%CAug 7, 2026
BoolQ0.821088.9%CAug 7, 2026
TriviaQA0.821894.1%CAug 7, 2026
PIQA0.831180.0%CAug 7, 2026
Social IQa0.54962.5%CAug 7, 2026
AGIEval0.651055.6%CAug 7, 2026
Winogrande0.862276.2%CAug 7, 2026
HellaSwag0.9102765.4%CAug 7, 2026
ARC-C0.7193445.5%CAug 7, 2026
MBPP0.6323713.9%CAug 7, 2026
GSM8k0.7424812.8%CAug 7, 2026
MATH0.465718.6%CAug 7, 2026
HumanEval0.571766.7%CAug 7, 2026
MMLU0.87610024.2%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

58 rows
Columns

Show columns

text style controlpolish1611350.458N/AAug 6, 2026
text style controljapanese1861228.91,808N/AAug 6, 2026
textpolish1881276.058N/AAug 6, 2026
textjapanese1911175.91,808N/AAug 6, 2026
text style controlkorean2051237.41,440N/AAug 6, 2026
text style controlfrench2081311.6793N/AAug 6, 2026
textkorean2091173.91,440N/AAug 6, 2026
textfrench2141246.1793N/AAug 6, 2026
text style controlspanish2141291.5845N/AAug 6, 2026
text style controlgerman2191269.32,037N/AAug 6, 2026
textspanish2221227.4845N/AAug 6, 2026
text style controlcreative writing2221292.511,429N/AAug 6, 2026
textgerman2281208.92,037N/AAug 6, 2026
text style controlindustry writing and literature and language2391297.020,390N/AAug 6, 2026
text style controlindustry entertainment and sports and media2411273.112,280N/AAug 6, 2026
text style controlrussian2431290.59,678N/AAug 6, 2026
text style controlchinese2461299.06,872N/AAug 6, 2026
textcreative writing2491241.011,429N/AAug 6, 2026
text style controlindustry legal and government2551311.24,458N/AAug 6, 2026
textrussian2561233.19,678N/AAug 6, 2026
textindustry writing and literature and language2571248.720,390N/AAug 6, 2026
text style controlindustry medicine and healthcare2571290.33,862N/AAug 6, 2026
text style controllonger query2571299.79,918N/AAug 6, 2026
text style controlnon english2581273.934,471N/AAug 6, 2026
text style controlmulti turn2591279.513,588N/AAug 6, 2026
textchinese2601220.16,872N/AAug 6, 2026
text style controloverall2631289.275,754N/AAug 6, 2026
text style controlindustry mathematical2631264.38,869N/AAug 6, 2026
text style controlinstruction following2641270.629,545N/AAug 6, 2026
textindustry entertainment and sports and media2651213.012,280N/AAug 6, 2026
textindustry legal and government2651241.24,458N/AAug 6, 2026
textnon english2651216.834,471N/AAug 6, 2026
text style controlexclude ties2661210.947,955N/AAug 6, 2026
text style controlindustry life and physical and social science2661304.012,863N/AAug 6, 2026
text style controlindustry software and it services2661310.119,950N/AAug 6, 2026
textindustry mathematical2671221.48,869N/AAug 6, 2026
textlonger query2671230.89,918N/AAug 6, 2026
text style controlexpert2671257.34,025N/AAug 6, 2026
text style controlindustry business and management and financial operations2671278.38,733N/AAug 6, 2026
textexpert2681170.74,025N/AAug 6, 2026
textmulti turn2681223.713,588N/AAug 6, 2026
textoverall2691231.675,754N/AAug 6, 2026
textexclude ties2691129.247,955N/AAug 6, 2026
textindustry medicine and healthcare2691196.93,862N/AAug 6, 2026
text style controlenglish2691299.141,283N/AAug 6, 2026
text style controlmath2691246.810,170N/AAug 6, 2026
textinstruction following2701206.429,545N/AAug 6, 2026
text style controlhard prompts2711282.020,494N/AAug 6, 2026
textindustry business and management and financial operations2731207.48,733N/AAug 6, 2026
textindustry software and it services2731228.919,950N/AAug 6, 2026
textmath2741212.010,170N/AAug 6, 2026
text style controlhard prompts english2741289.212,606N/AAug 6, 2026
textindustry life and physical and social science2751228.512,863N/AAug 6, 2026
textenglish2761242.141,283N/AAug 6, 2026
textcoding2781211.412,088N/AAug 6, 2026
text style controlcoding2781304.612,088N/AAug 6, 2026
texthard prompts2801198.720,494N/AAug 6, 2026
texthard prompts english2811207.612,606N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.65 input, $0.65 output per 1M via OpenRouter
Tracked offerings
1
1 rows
Columns

Show columns

OpenRoutergoogle/gemma-2-27b-itglobal$0.65$0.658.2KAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Gemma 2 27B versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

Gemma 2 27BJun 27, 202447.127.2BN/AN/ANoGemma

What is Gemma 2 27B?

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.

Gemma 2 27B vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

Gemma 2 27BvsQwen3.6 35B A3BGemma 2 27BvsGemma 4 12BGemma 2 27BvsPhi 4 ReasoningGemma 2 27BvsSarvam 30BGemma 2 27BvsQwen2.5 Coder 32BGemma 2 27BvsGemma 3 27B

Models similar to Gemma 2 27B

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#91+1.1
GO

Gemma 4 12B

Google

48.1 LLMBoard

DetailsCompare
#87+1.5
GO

Gemini 1.5 Pro

Google

48.6 LLMBoard

DetailsCompare
#96-1.9
GO

Gemma 3 27B

Google

45.1 LLMBoard

DetailsCompare
#76+5.5
GO

Gemini 2.0 Flash Lite

Google

52.6 LLMBoard

DetailsCompare
#73+6.0
GO

Gemini 2.0 Flash

Google

53.1 LLMBoard

DetailsCompare
#116-7.9
GO

Gemma 3 12B

Google

39.2 LLMBoard

DetailsCompare

FAQ

Common questions about Gemma 2 27B.

When was Gemma 2 27B released?

Gemma 2 27B's default version was released on Jun 27, 2024.

How much does Gemma 2 27B cost?

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.

Who created Gemma 2 27B?

Gemma 2 27B is published under Google in the model registry.

What is the context window for Gemma 2 27B?

The current registry does not publish a context window for the default version.

Is Gemma 2 27B open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer Gemma 2 27B?

1 published provider offerings are linked to the default version.

What models should I compare Gemma 2 27B with?

Nearby ranked alternatives include Qwen3.6 35B A3B, Gemma 4 12B, Phi 4 Reasoning.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai