Intelligence
26 scoreGoogle · Flagships Analysis
Gemma 4 26B A4B
Intelligence, Performance & Price Analysis
Canonical slug: gemma-4-26b-a4b · Canonical model registry at build time
Input Price
$0.13 / 1M tokensOutput Price
$0.40 / 1M tokensVerbosity
74M Output tokens from Intelligence Index 4 out of 4 units for Verbosity . CompaExecutive Assessment
Routing Verdict & Tradeoffs
Ethen Routing Verdict
Strong general-purpose model
Gemma 4 26B A4B (Reasoning) scores 26 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9). Gemma 4 26B A4B (Reasoning) costs $0.13 per 1M input tokens (better than average, median: $0.18) and $0.40 per 1M output tokens (better than average, median: $0.40), based on the median across providers serving the model.
Suitable for most production tasks, but high-volume or repetitive work should still be compared against cheaper routes.
Task Fit Assessment
| Workload | Rating | Notes |
|---|---|---|
| Complex reasoning & agentic workflows | optimal | Intelligence score 26 supports capable reasoning, but very hard tasks may benefit from higher-tier models. |
| Cost-sensitive pipelines | optimal | Output pricing at $0.40 is very competitive for high-volume workloads. |
Cost Pressure Analysis
Low
Pricing is competitive — input $0.13, output $0.40. Suitable for sustained production use.
Technical Specifications
Architecture and Limits
| Specification | Value | Validation Authority |
|---|---|---|
| Model type | Open weights | inferred |
| Reasoning | Yes | faq |
| Input modalities | Gemma 4 26B A4B (Reasoning) supports text, image, and video input. | faq |
| Output modalities | Gemma 4 26B A4B (Reasoning) supports text output. | faq |
| Context window | 260k tokens | faq |
| Open weights / source | Yes, Gemma 4 26B A4B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting. | faq |
| Parameters | Gemma 4 26B A4B (Reasoning) has 25.2 billion parameters (3.8 billion active). | faq |
| Active parameters | Gemma 4 26B A4B (Reasoning) is a Mixture of Experts (MoE) model with 25.2 billion total parameters, but only 3.8 billion active parameters are used during inference. | faq |
| License | Gemma 4 26B A4B (Reasoning) is released under the Apache 2.0 license. This license allows commercial use. | faq |
| API availability | Yes, Gemma 4 26B A4B (Reasoning) is available via API through 8 providers. | faq |
Evidence charts
Profile visualizations
Charts are the same canonical evidence cards previously published for this slug, contained inside the D18D page grammar.
AA-Omniscience Index
AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Openness Index: Score
Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open) · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Intelligence
Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
Context Window
Context window: tokens limit · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Larger context windows enable complex multi-turn tasks but may increase latency and cost for long inputs.
Cost per Intelligence Index Task
Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost per Task
Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost to Run Artificial Analysis Intelligence Index
Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Pricing: Cache Hit, Input, and Output
Price (USD per M Tokens) · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Model Size: Total and Active Parameters
Comparison between total model parameters and parameters active during inference · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Larger models generally perform better but cost more to serve. Active parameter count matters for inference efficiency.
Output Tokens per Intelligence Index Task
Weighted average number of output tokens used to run one task in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Methodology
Methodology & Provenance
This page is rendered from the normalized profile and page JSON for Gemma 4 26B A4B.
Benchmark values are preserved as normalized; only layout, disclosure ordering, and typography are adjusted for readability.
Frequently Asked Questions
Model FAQs & Technical Disclosures
Gemma 4 26B A4B (Reasoning) was released on April 2, 2026.
Gemma 4 26B A4B (Reasoning) was created by Google.
Gemma 4 26B A4B (Reasoning) scores 26 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9).
Gemma 4 26B A4B (Reasoning) costs $0.13 per 1M input tokens (better than average, median: $0.18) and $0.40 per 1M output tokens (better than average, median: $0.40), based on the median across providers serving the model.
Gemma 4 26B A4B (Reasoning) costs $0.13 per 1M input tokens and $0.40 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.13 per 1M tokens. Pricing may vary by provider.
When evaluated on the Intelligence Index, Gemma 4 26B A4B (Reasoning) generated 74M output tokens, which is somewhat higher than average compared to other open weight models of similar size (median: 32M).
Yes, Gemma 4 26B A4B (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Gemma 4 26B A4B (Reasoning) supports text, image, and video input.
Gemma 4 26B A4B (Reasoning) supports text output.
Yes, Gemma 4 26B A4B (Reasoning) supports image input and can analyze, describe, and answer questions about images.
Yes, Gemma 4 26B A4B (Reasoning) is multimodal. It can process text, image, and video input and generate text output.
Gemma 4 26B A4B (Reasoning) has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Gemma 4 26B A4B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Gemma 4 26B A4B (Reasoning) has 25.2 billion parameters (3.8 billion active).
Gemma 4 26B A4B (Reasoning) is a Mixture of Experts (MoE) model with 25.2 billion total parameters, but only 3.8 billion active parameters are used during inference.
Gemma 4 26B A4B (Reasoning) is released under the Apache 2.0 license. This license allows commercial use.
Gemma 4 26B A4B (Reasoning) achieves a score of 26 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Gemma 4 26B A4B (Reasoning) is available via API through 8 providers.
Gemma 4 26B A4B (Reasoning) is available through 8 API providers.