Google: Gemma 3 27B
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning,…
google/gemma-3-27b-it
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)
Specifications & capabilities
- Input
- text, image
- Output
- text
- Context window · tokens
- 131072
- Knowledge cutoff
- 2024-08-31
- Published model ID
- gemma3@gemma-3-27b-it
- Capabilities
- multimodal, promptCaching, structuredOutputs, toolCalling, visionInput
Description source ↗Evaluations
41–60 / 153
81.1%
- source id
- mmBench
- leaderboard name
- image_emotion
- dimension
- vision
- metric
- image_emotion
- rank
- 86
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_CN_V11_Data
- verified
- Yes
- metric_kind
- image_emotion
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- mmbench-data.json
- source_revision
- acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
- metric_population
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-27B
Original result ↗79.8%
- source id
- mmBench
- leaderboard name
- CP
- dimension
- vision
- metric
- CP
- rank
- 90
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_EN_V11_Data
- verified
- Yes
- metric_kind
- CP
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- mmbench-data.json
- source_revision
- acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
- metric_population
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-27B
Original result ↗1,165.585
- source id
- lmarena
- leaderboard name
- LMArena Vision Humor
- dimension
- multimodal
- metric
- Arena rating
- rank
- 94
- sample size
- 762
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 27B IT
- confidence lower
- 1141.2469213795798
- confidence upper
- 1189.9239676129957
Original result ↗1,152.95
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control Humor
- dimension
- multimodal
- metric
- Arena rating
- rank
- 94
- sample size
- 762
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 27B IT
- confidence lower
- 1128.173315566545
- confidence upper
- 1177.7259822805631
Original result ↗1,167.074
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control Creative Writing Vision
- dimension
- multimodal
- metric
- Arena rating
- rank
- 96
- sample size
- 626
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 27B IT
- confidence lower
- 1141.4205828300485
- confidence upper
- 1192.7272045182742
Original result ↗91.1%
- source id
- mmBench
- leaderboard name
- function_reasoning
- dimension
- vision
- metric
- function_reasoning
- rank
- 96
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_CN_V11_Data
- verified
- Yes
- metric_kind
- function_reasoning
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- mmbench-data.json
- source_revision
- acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
- metric_population
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-27B
Original result ↗1,176.746
- source id
- lmarena
- leaderboard name
- LMArena Vision Creative Writing Vision
- dimension
- multimodal
- metric
- Arena rating
- rank
- 97
- sample size
- 626
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 27B IT
- confidence lower
- 1151.3869377357726
- confidence upper
- 1202.104160051268
Original result ↗57.3%
- source id
- mmBench
- leaderboard name
- spatial_relationship
- dimension
- vision
- metric
- spatial_relationship
- rank
- 100
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_EN_V11_Data
- verified
- Yes
- metric_kind
- spatial_relationship
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- mmbench-data.json
- source_revision
- acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
- metric_population
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-27B
Original result ↗1,173.608
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control Chinese
- dimension
- multimodal
- metric
- Arena rating
- rank
- 102
- sample size
- 1019
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 27B IT
- confidence lower
- 1152.1549838196281
- confidence upper
- 1195.061735419797
Original result ↗1,163.35
- source id
- lmarena
- leaderboard name
- LMArena Vision Chinese
- dimension
- multimodal
- metric
- Arena rating
- rank
- 103
- sample size
- 1019
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 27B IT
- confidence lower
- 1142.4805298687697
- confidence upper
- 1184.2188570608346
Original result ↗53.3%
- source id
- mmBench
- leaderboard name
- spatial_relationship
- dimension
- vision
- metric
- spatial_relationship
- rank
- 103
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_CN_V11_Data
- verified
- Yes
- metric_kind
- spatial_relationship
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- mmbench-data.json
- source_revision
- acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
- metric_population
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-27B
Original result ↗1,187.939
- source id
- lmarena
- leaderboard name
- LMArena Vision English
- dimension
- multimodal
- metric
- Arena rating
- rank
- 105
- sample size
- 7918
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 27B IT
- confidence lower
- 1177.5720968917394
- confidence upper
- 1198.3066813554597
Original result ↗85.6%
- source id
- mmBench
- leaderboard name
- FP-S
- dimension
- vision
- metric
- FP-S
- rank
- 105
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_EN_V11_Data
- verified
- Yes
- metric_kind
- FP-S
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- mmbench-data.json
- source_revision
- acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
- metric_population
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-27B
Original result ↗76%
- source id
- mmBench
- leaderboard name
- future_prediction
- dimension
- vision
- metric
- future_prediction
- rank
- 105
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_EN_V11_Data
- verified
- Yes
- metric_kind
- future_prediction
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- mmbench-data.json
- source_revision
- acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
- metric_population
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-27B
Original result ↗79.6%
- source id
- mmBench
- leaderboard name
- Overall
- dimension
- vision
- metric
- Overall
- rank
- 106
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_EN_V11_Data
- verified
- Yes
- metric_kind
- Overall
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- mmbench-data.json
- source_revision
- acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
- metric_population
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-27B
Original result ↗67.9%
- source id
- mmBench
- leaderboard name
- LR
- dimension
- vision
- metric
- LR
- rank
- 106
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_EN_V11_Data
- verified
- Yes
- metric_kind
- LR
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- mmbench-data.json
- source_revision
- acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
- metric_population
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-27B
Original result ↗62.4%
- source id
- mmBench
- leaderboard name
- structuralized_imagetext_understanding
- dimension
- vision
- metric
- structuralized_imagetext_understanding
- rank
- 107
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_EN_V11_Data
- verified
- Yes
- metric_kind
- structuralized_imagetext_understanding
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- mmbench-data.json
- source_revision
- acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
- metric_population
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-27B
Original result ↗1,173.746
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control English
- dimension
- multimodal
- metric
- Arena rating
- rank
- 109
- sample size
- 7918
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 27B IT
- confidence lower
- 1163.238407261123
- confidence upper
- 1184.253092783513
Original result ↗92.2%
- source id
- mmBench
- leaderboard name
- function_reasoning
- dimension
- vision
- metric
- function_reasoning
- rank
- 109
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_EN_V11_Data
- verified
- Yes
- metric_kind
- function_reasoning
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- mmbench-data.json
- source_revision
- acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
- metric_population
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-27B
Original result ↗1,169.23
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control Homework
- dimension
- multimodal
- metric
- Arena rating
- rank
- 110
- sample size
- 1034
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 27B IT
- confidence lower
- 1150.211002373117
- confidence upper
- 1188.2493853315916
Original result ↗Published prices
1–7 / 7
$0.09
- Inference provider
- cheaperInference
- Platform
- Cheaper Inference
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- zdr
- false
- protocol
- chat_completions
- service_tier
- standard
- Billing label
- Input tokens (per 1M)
$0.33
- Inference provider
- cheaperInference
- Platform
- Cheaper Inference
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- zdr
- false
- protocol
- chat_completions
- service_tier
- standard
- Billing label
- Output tokens (per 1M)
$0.08
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- input_tokens_per_million
- Currency
- USD
$0.16
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- output_tokens_per_million
- Currency
- USD
$0.04
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
$0.08
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$0.35
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
Provider specifications & access
1–4 / 4
- source model id
- gemma-3-27b-it
- hosting
- gateway
- context length
- 40000
- max output tokens
- 16384
- capabilities
- structuredOutputs
- toolCalling
- source model id
- google.gemma-3-27b-it
- hosting
- bedrock-managed
- source model id
- publishers/google/models/gemma3@gemma-3-27b-it
- hosting
- vertex-self-deployed
- source model id
- publishers/hf-google/models/gemma-3-27b-it@001
- hosting
- vertex-self-deployed
Safety assessments
1–1 / 1
41 / 100
- source id
- stanfordFMTI
- canonical model id
- google/gemma-3-27b-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
- 131072
- normalized value
- 131072
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2024-08-31
- normalized value
- 2024-08-31
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 117964
- normalized value
- 117964
- scope
- source-model
- source id
- openRouter
- confidence
- 1
Explore more models