Google: Gemma 2 27B
Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...
google/gemma-2-27b-it
Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...
Specifications & capabilities
- Input
- text
- Output
- text
- Context window · tokens
- 8192
- Knowledge cutoff
- 2024-06-30
- Published model ID
- gemma2@gemma-2-27b-it
- Capabilities
- structuredOutputs
Evaluations
1–20 / 82
95.98%
- source id
- openPersianLLM
- leaderboard name
- ARC Easy
- dimension
- general
- metric
- ARC Easy
- rank
- 1
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- Open Persian LLM
- language
- fa
- precision
- bfloat16
- metric_kind
- ARC Easy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- PartAI/open-persian-llm-leaderboard/leaderboard_data.jsonl
- published_at
- 2025-12-06T10:13:22Z
- source_revision
- 92771e7359b0679b2f851b2a34e98c6ce2ccbf29bb5ae60b12bee0bd0319286e
- metric_population
- 27
- benchmark_evaluation
- true
- source model id
- google/gemma-2-27b-it
Original result ↗63.12%
- source id
- openPersianLLM
- leaderboard name
- AUT Multiple Choice Persian
- dimension
- general
- metric
- AUT Multiple Choice Persian
- rank
- 3
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- Open Persian LLM
- language
- fa
- precision
- bfloat16
- metric_kind
- AUT Multiple Choice Persian
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- PartAI/open-persian-llm-leaderboard/leaderboard_data.jsonl
- published_at
- 2025-12-06T10:13:22Z
- source_revision
- 92771e7359b0679b2f851b2a34e98c6ce2ccbf29bb5ae60b12bee0bd0319286e
- metric_population
- 27
- benchmark_evaluation
- true
- source model id
- google/gemma-2-27b-it
Original result ↗85.91%
- source id
- openPersianLLM
- leaderboard name
- ARC Challenge
- dimension
- general
- metric
- ARC Challenge
- rank
- 4
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- Open Persian LLM
- language
- fa
- precision
- bfloat16
- metric_kind
- ARC Challenge
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- PartAI/open-persian-llm-leaderboard/leaderboard_data.jsonl
- published_at
- 2025-12-06T10:13:22Z
- source_revision
- 92771e7359b0679b2f851b2a34e98c6ce2ccbf29bb5ae60b12bee0bd0319286e
- metric_population
- 27
- benchmark_evaluation
- true
- source model id
- google/gemma-2-27b-it
Original result ↗46.03%
- source id
- openPersianLLM
- leaderboard name
- Part Multiple Choice
- dimension
- general
- metric
- Part Multiple Choice
- rank
- 5
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- Open Persian LLM
- language
- fa
- precision
- bfloat16
- metric_kind
- Part Multiple Choice
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- PartAI/open-persian-llm-leaderboard/leaderboard_data.jsonl
- published_at
- 2025-12-06T10:13:22Z
- source_revision
- 92771e7359b0679b2f851b2a34e98c6ce2ccbf29bb5ae60b12bee0bd0319286e
- metric_population
- 27
- benchmark_evaluation
- true
- source model id
- google/gemma-2-27b-it
Original result ↗36.28%
- source id
- openPersianLLM
- leaderboard name
- MMLU Pro
- dimension
- general
- metric
- MMLU Pro
- rank
- 5
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- Open Persian LLM
- language
- fa
- precision
- bfloat16
- metric_kind
- MMLU Pro
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- PartAI/open-persian-llm-leaderboard/leaderboard_data.jsonl
- published_at
- 2025-12-06T10:13:22Z
- source_revision
- 92771e7359b0679b2f851b2a34e98c6ce2ccbf29bb5ae60b12bee0bd0319286e
- metric_population
- 27
- benchmark_evaluation
- true
- source model id
- google/gemma-2-27b-it
Original result ↗0.518
- source id
- llmStatsArchive
- leaderboard name
- HumanEval · Normalized (reported)
- dimension
- general
- metric
- HumanEval · Normalized (reported)
- rank
- 9
- aggregation scope
- status
- archived
- license
- CC-BY-4.0
- direction
- higherIsBetter
- conditions
- language
- en
- benchmark
- name
- HumanEval
- language
- en
- modality
- text
- verified
- false
- max_score
- 1
- created_at
- 2025-07-19T19:56:12.595263+00:00
- paper_link
- https://arxiv.org/abs/2107.03374
- updated_at
- 2025-07-19T19:56:12.595263+00:00
- description
- A benchmark that measures functional correctness for synthesizing programs from docstrings, consisting of 164 original programming problems assessing language comprehension, algorithms, and simple mathematics
- benchmark_id
- humaneval
- multilingual
- false
- analysis_method
- pass@1
- is_self_reported
- true
- verified_by_llmstats
- false
- attribution
- Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
- license_url
- https://creativecommons.org/licenses/by/4.0/
- metric_kind
- HumanEval · Normalized (reported)
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- data/organizations/google/models/gemma-2-27b-it/benchmarks.json
- archive_kind
- llmStats
- evidence_url
- https://huggingface.co/blog/gemma2
- git_revision
- 872b75f63b8d853c46ed17856424029a0c47b1d2
- published_at
- 2025-10-24T17:47:59Z
- snapshot_date
- 2025-10-24T17:47:59Z
- source_revision
- 6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
- publisher_anchor
- google/gemma-2-27b-it
- metric_population
- 10
- current_catalog_url
- https://llm-stats.com/
- benchmark_evaluation
- true
- source model id
- gemma-2-27b-it
Original result ↗0.518
- source id
- llmStatsArchive
- leaderboard name
- HumanEval · Raw
- dimension
- general
- metric
- HumanEval · Raw
- rank
- 9
- aggregation scope
- status
- archived
- license
- CC-BY-4.0
- direction
- higherIsBetter
- conditions
- language
- en
- benchmark
- name
- HumanEval
- language
- en
- modality
- text
- verified
- false
- max_score
- 1
- created_at
- 2025-07-19T19:56:12.595263+00:00
- paper_link
- https://arxiv.org/abs/2107.03374
- updated_at
- 2025-07-19T19:56:12.595263+00:00
- description
- A benchmark that measures functional correctness for synthesizing programs from docstrings, consisting of 164 original programming problems assessing language comprehension, algorithms, and simple mathematics
- benchmark_id
- humaneval
- multilingual
- false
- analysis_method
- pass@1
- is_self_reported
- true
- verified_by_llmstats
- false
- attribution
- Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
- license_url
- https://creativecommons.org/licenses/by/4.0/
- metric_kind
- HumanEval · Raw
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- data/organizations/google/models/gemma-2-27b-it/benchmarks.json
- archive_kind
- llmStats
- evidence_url
- https://huggingface.co/blog/gemma2
- git_revision
- 872b75f63b8d853c46ed17856424029a0c47b1d2
- published_at
- 2025-10-24T17:47:59Z
- snapshot_date
- 2025-10-24T17:47:59Z
- source_revision
- 6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
- publisher_anchor
- google/gemma-2-27b-it
- metric_population
- 10
- current_catalog_url
- https://llm-stats.com/
- benchmark_evaluation
- true
- source model id
- gemma-2-27b-it
Original result ↗68.816%
- source id
- liveBench
- leaderboard name
- LiveBench Instruction Following
- dimension
- general
- metric
- Average score
- rank
- 79
- sample size
- 76
- evaluated at
- 2024-12-10T19:31:49.659Z
- source model id
- gemma-2-27b-it
Original result ↗34.042%
- source id
- liveBench
- leaderboard name
- LiveBench Language
- dimension
- intelligence
- metric
- Average score
- rank
- 81
- sample size
- 290
- evaluated at
- 2025-02-06T20:21:52.929Z
- source model id
- gemma-2-27b-it
Original result ↗39.883%
- source id
- liveBench
- leaderboard name
- LiveBench Overall
- dimension
- general
- metric
- Average score
- rank
- 84
- sample size
- 494
- evaluated at
- 2025-02-06T20:21:52.929Z
- source model id
- gemma-2-27b-it
Original result ↗35.938%
- source id
- liveBench
- leaderboard name
- LiveBench Coding
- dimension
- coding
- metric
- Average score
- rank
- 90
- sample size
- 128
- evaluated at
- 2024-12-10T19:07:16.333Z
- source model id
- gemma-2-27b-it
Original result ↗79.777%
- source id
- openLLMLeaderboardV2
- leaderboard name
- Open LLM v2 IFEval · Normalized
- dimension
- instructionFollowing
- metric
- Normalized score
- rank
- 136
- aggregation scope
- suite
- Open LLM v2
- co2_kg
- 9.652422373385473
- status
- archived
- precision
- bfloat16
- task_count
- 6
- metric_kind
- Normalized score
- rank_method
- Derived competition rank over published evaluations with reported scores, including variants and source flags
- weight_type
- Original
- published_at
- 2025-03-20T12:17:27Z
- chat_template
- true
- suite_version
- 2
- model_revision
- f6c533e5eb013c7e31fc74ef042ac4f3fb5cf40b
- source_flagged
- false
- dataset_revision
- 9c09a7cae43334062a82cb164f2ef255013dafa2
- metric_population
- 4576
- ranking_population
- 4576
- source_flag_anomaly
- false
- source model id
- google/gemma-2-27b-it
Original result ↗79.777%
- source id
- openLLMLeaderboardV2
- leaderboard name
- Open LLM v2 IFEval · Raw
- dimension
- instructionFollowing
- metric
- Raw accuracy
- rank
- 136
- aggregation scope
- suite
- Open LLM v2
- co2_kg
- 9.652422373385473
- status
- archived
- precision
- bfloat16
- task_count
- 6
- metric_kind
- Raw accuracy
- rank_method
- Derived competition rank over published evaluations with reported scores, including variants and source flags
- weight_type
- Original
- published_at
- 2025-03-20T12:17:27Z
- chat_template
- true
- suite_version
- 2
- model_revision
- f6c533e5eb013c7e31fc74ef042ac4f3fb5cf40b
- source_flagged
- false
- dataset_revision
- 9c09a7cae43334062a82cb164f2ef255013dafa2
- metric_population
- 4576
- ranking_population
- 4576
- source_flag_anomaly
- false
- source model id
- google/gemma-2-27b-it
Original result ↗1,350.999
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Polish
- dimension
- style
- metric
- Arena rating
- rank
- 187
- sample size
- 58
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 2 27B IT
- confidence lower
- 1274.1150619542495
- confidence upper
- 1427.8822006010364
Original result ↗1,277.078
- source id
- lmarena
- leaderboard name
- LMArena Text Polish
- dimension
- general
- metric
- Arena rating
- rank
- 216
- sample size
- 58
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 2 27B IT
- confidence lower
- 1204.1014311410802
- confidence upper
- 1350.0537453506981
Original result ↗1,229.459
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Japanese
- dimension
- style
- metric
- Arena rating
- rank
- 223
- sample size
- 1808
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 2 27B IT
- confidence lower
- 1213.3796838812934
- confidence upper
- 1245.5376617701556
Original result ↗1,175.694
- source id
- lmarena
- leaderboard name
- LMArena Text Japanese
- dimension
- general
- metric
- Arena rating
- rank
- 227
- sample size
- 1808
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 2 27B IT
- confidence lower
- 1159.709178212857
- confidence upper
- 1191.6793851135092
Original result ↗1,237.954
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Korean
- dimension
- style
- metric
- Arena rating
- rank
- 233
- sample size
- 1440
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 2 27B IT
- confidence lower
- 1218.5595196004615
- confidence upper
- 1257.3488444647455
Original result ↗1,173.887
- source id
- lmarena
- leaderboard name
- LMArena Text Korean
- dimension
- general
- metric
- Arena rating
- rank
- 236
- sample size
- 1440
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 2 27B IT
- confidence lower
- 1154.551872554006
- confidence upper
- 1193.2229027140606
Original result ↗1,312.165
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control French
- dimension
- style
- metric
- Arena rating
- rank
- 239
- sample size
- 793
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 2 27B IT
- confidence lower
- 1288.8333183334032
- confidence upper
- 1335.4975361758372
Original result ↗Published prices
1–4 / 4
$0.27
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- input_tokens_per_million
- Currency
- USD
$0.27
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- output_tokens_per_million
- Currency
- USD
$0.65
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$0.65
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
Provider specifications & access
1–2 / 2
- source model id
- publishers/google/models/gemma2@gemma-2-27b-it
- hosting
- vertex-self-deployed
- source model id
- publishers/hf-google/models/gemma-2-27b-it@001
- hosting
- vertex-self-deployed
Safety assessments
1–1 / 1
41 / 100
- source id
- stanfordFMTI
- canonical model id
- google/gemma-2-27b-it
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- Google
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 41 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Source specification observations
1–3 / 3
- field
- context_length
- value
- 8192
- normalized value
- 8192
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2024-06-30
- normalized value
- 2024-06-30
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 2048
- normalized value
- 2048
- scope
- source-model
- source id
- openRouter
- confidence
- 1
Explore more models