Intelligence
29 scoreGoogle · Flagships Analysis
Gemma 4 31B
Intelligence, Performance & Price Analysis
Canonical slug: gemma-4-31b · Canonical model registry at build time
Speed
34.4 output tokens/secLatency
1.00s TTFTInput Price
$0.00Output Price
$0.00Verbosity
38M Output tokens from Intelligence Index 3 out of 4 units for Verbosity . CompaExecutive Assessment
Routing Verdict & Tradeoffs
Ethen Routing Verdict
Strong general-purpose model
Gemma 4 31B (Reasoning) scores 29 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9). Gemma 4 31B (Reasoning) generates output at 34.4 tokens per second (based on Google's API), which is at the lower end compared to other open weight models of similar size (median: 101.8 t/s).
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 29 supports capable reasoning, but very hard tasks may benefit from higher-tier models. |
| High-volume chat & customer-facing | viable | Output speed may be a bottleneck for real-time chat at scale. |
| Latency-sensitive applications | optimal | TTFT 1.00s — adequate latency for most interactive use cases. |
| Cost-sensitive pipelines | optimal | Output pricing at $0.00 is very competitive for high-volume workloads. |
Cost Pressure Analysis
Low
Pricing is competitive — input $0.00, output $0.00. 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 31B (Reasoning) supports text, image, and video input. | faq |
| Output modalities | Gemma 4 31B (Reasoning) supports text output. | faq |
| Context window | 260k tokens | faq |
| Open weights / source | Yes, Gemma 4 31B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting. | faq |
| Parameters | Gemma 4 31B (Reasoning) has 30.7 billion parameters. | faq |
| License | Gemma 4 31B (Reasoning) is released under the Apache 2.0 license. This license allows commercial use. | faq |
| API availability | Yes, Gemma 4 31B (Reasoning) is available via API through 12 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.
Output 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.
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.
End-to-End Response Time
Seconds to output 500 tokens, including reasoning model 'thinking' time · 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.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Latency: Time To First Answer Token
Seconds to first answer token received · Accounts for reasoning model 'thinking' time · 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.
Latency includes thinking / reasoning time when applicable. Lower is better for interactive use cases.
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.
Time per Intelligence Index Task
Weighted average decode time (minutes) per task; excludes TTFT and overhead time · 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.
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 31B.
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 31B (Reasoning) was released on April 2, 2026.
Gemma 4 31B (Reasoning) was created by Google.
Gemma 4 31B (Reasoning) scores 29 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9).
Gemma 4 31B (Reasoning) generates output at 34.4 tokens per second (based on Google's API), which is at the lower end compared to other open weight models of similar size (median: 101.8 t/s).
Gemma 4 31B (Reasoning) has a time to first token (TTFT) of 1.00s (based on Google's API), which is better than average compared to other open weight models of similar size (median: 2.08s).
When evaluated on the Intelligence Index, Gemma 4 31B (Reasoning) generated 38M output tokens, which is somewhat higher than average compared to other open weight models of similar size (median: 32M).
Yes, Gemma 4 31B (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 31B (Reasoning) supports text, image, and video input.
Gemma 4 31B (Reasoning) supports text output.
Yes, Gemma 4 31B (Reasoning) supports image input and can analyze, describe, and answer questions about images.
Yes, Gemma 4 31B (Reasoning) is multimodal. It can process text, image, and video input and generate text output.
Gemma 4 31B (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 31B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Gemma 4 31B (Reasoning) has 30.7 billion parameters.
Gemma 4 31B (Reasoning) is released under the Apache 2.0 license. This license allows commercial use.
Gemma 4 31B (Reasoning) achieves a score of 29 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Gemma 4 31B (Reasoning) is available via API through 12 providers.
Gemma 4 31B (Reasoning) is available through 12 API providers.