Gemma 4 26B A4B
Not tested yet
Language modelActive
Gemma 4 26B A4B
- Released
- March 31, 2026
- Data date
- September 8, 2026
- Intelligence
- Overall score
- Price
- Input · Output / 1M tokens
- Input
- Text, Image
- Output
- Text
No published category-wide ranking is available for this model.
Entries 1-12 of 17. Page 1 of 2.
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
MMLU Pro (Show measurement, test conditions, and source)
- Source value
- 82.6
- Score
- 82.6
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:gemma-4-26b-a4b:0
- Source type
- vendor-reported
- Evaluator
- Google DeepMind
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Gemma 4 model-card benchmark table; 26B A4B column
AIME 2026 (no tools) (Show measurement, test conditions, and source)
- Source value
- 88.3
- Score
- 88.3
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:gemma-4-26b-a4b:1
- Source type
- vendor-reported
- Evaluator
- Google DeepMind
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Gemma 4 model-card benchmark table; 26B A4B column
LiveCodeBench v6 (Show measurement, test conditions, and source)
- Source value
- 77.1
- Score
- 77.1
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:gemma-4-26b-a4b:2
- Source type
- vendor-reported
- Evaluator
- Google DeepMind
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Gemma 4 model-card benchmark table; 26B A4B column
GPQA (Show measurement, test conditions, and source)
- Source value
- 82.3
- Score
- 82.3
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:gemma-4-26b-a4b:4
- Source type
- vendor-reported
- Evaluator
- Google DeepMind
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Gemma 4 model-card benchmark table; 26B A4B column
Tau2 (Show measurement, test conditions, and source)
- Source value
- 68.2
- Score
- 68.2
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:gemma-4-26b-a4b:5
- Source type
- vendor-reported
- Evaluator
- Google DeepMind
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Gemma 4 model-card benchmark table; 26B A4B column
Humanity's Last Exam (no tools) (Show measurement, test conditions, and source)
- Source value
- 8.7
- Score
- 8.7
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:gemma-4-26b-a4b:6
- Source type
- vendor-reported
- Evaluator
- Google DeepMind
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Gemma 4 model-card benchmark table; 26B A4B column
Humanity's Last Exam (search) (Show measurement, test conditions, and source)
- Source value
- 17.2
- Score
- 17.2
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:gemma-4-26b-a4b:7
- Source type
- vendor-reported
- Evaluator
- Google DeepMind
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Gemma 4 model-card benchmark table; 26B A4B column
BigBench Extra Hard (Show measurement, test conditions, and source)
- Source value
- 64.8
- Score
- 64.8
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:gemma-4-26b-a4b:8
- Source type
- vendor-reported
- Evaluator
- Google DeepMind
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Gemma 4 model-card benchmark table; 26B A4B column
MMMLU (Show measurement, test conditions, and source)
- Source value
- 86.3
- Score
- 86.3
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:gemma-4-26b-a4b:9
- Source type
- vendor-reported
- Evaluator
- Google DeepMind
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Gemma 4 model-card benchmark table; 26B A4B column
MMMU Pro (Show measurement, test conditions, and source)
- Source value
- 73.8
- Score
- 73.8
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:gemma-4-26b-a4b:10
- Source type
- vendor-reported
- Evaluator
- Google DeepMind
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Gemma 4 model-card benchmark table; 26B A4B column
MATH-Vision (Show measurement, test conditions, and source)
- Source value
- 82.4
- Score
- 82.4
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:gemma-4-26b-a4b:12
- Source type
- vendor-reported
- Evaluator
- Google DeepMind
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Gemma 4 model-card benchmark table; 26B A4B column
MedXpertQA (Show measurement, test conditions, and source)
- Source value
- 58.1
- Score
- 58.1
- Metric
- percent
- Unit
- %
- Category
- vendor-evaluation
- Direction
- Higher is better
- Comparison cohort
- research:gemma-4-26b-a4b:13
- Source type
- vendor-reported
- Evaluator
- Google DeepMind
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Gemma 4 model-card benchmark table; 26B A4B column
Our model tests
Community tests you can inspect
Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.
Pelican on a bicycle
A community classic for free-form SVG drawing.
Prompt and test conditions
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)Profile
Specifications and access
Published information about this model. Existing estimates are explicitly labeled.
Additional source observations
Dated documentation and model-card observations. Provider limits, native context and extended context can differ. Configuration notes retain the source wording.
- Release
- 2026-03-31Source
- Parameters
- 25.2 BSource
- Input
- Text, ImageSource
- Output
- TextSource
- Architecture
- Mixture-of-experts transformer, 25.2B total and 3.8B active; hybrid sliding/global attentionSource
- License
- Apache 2.0Source
- Knowledge cutoff
- 2025-01Source
- Context window
- 262,144 tokensSource
- Active parameters
- 3.8 BSource
- Languages
- 140+Source
- Announcement
- 2026-04-02Source
Pricing
Published prices
Prices apply to the stated unit. Resolution, output length, and provider can change the cost.
Cost example
100 API requests
$0.024
100 requests with 1,000 input and 500 output tokens each calculate to $0.024. Input accounts for $0.007; output accounts for $0.017.
- Input price
- $0.07 / 1M tokensBase tier for each request
- Output price
- $0.34 / 1M tokensBase tier for each request
The calculation uses documented token prices and no cache discount. It excludes extra tools, tax, reasoning tokens, and further hidden output tokens.
Open sourceHead-to-head comparisons
Compare this model
Each matchup compares this model with exactly one other model from the same category.
There are no published direct comparisons for this model yet.
More models
Models from the same selection
All AI models
Evidence
Sources and data date
Every statement links to its underlying documentation or leaderboard.
- Price
Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs.
- Input
Documented modalities. Retrieved September 8, 2026.
- Output
Documented modalities. Retrieved September 8, 2026.
Research date September 8, 2026. 4 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Open evidence questions and research notes (original wording)
Not found in the inspected sources
active-parameters-billions. Active parameter count is not separately published for this dense model.
Not found in the inspected sources
api-model-id. Gemma is distributed as open weights; the card does not define a hosted Gemini API model ID.
Not found in the inspected sources
training-tokens. The Gemma 4 model card describes the dataset but does not publish a token-count total.