Google, open weights

# Gemma 3 4B

> Gemma 3 4B by Google, released March 2025. Ranked #326 of 354 with a Noometry Index of 28.1. API: $0.04 in / $0.08 out per M tokens. 131K context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/gemma-3-4b
- Last updated: 2026-10-10
- Title: Gemma 3 4B Benchmarks, Price & Rank (October 2026)

Gemma 3 4B by Google ranks 326th of 354 ranked models on the Noometry Index as of October 2026, with a score of 28.1. Its strongest category is agentic & tool use, where it ranks 142nd. API pricing starts at $0.04 per million input tokens and $0.08 per million output tokens, with a 131K-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #326 of 354
- **Index score:** 28.1
- **Evidence:** Confirmed 22 results
- **Provider:** [![](/logos/google.svg) Google](https://noometry.com/providers/google)
- **Released:** March 12, 2025
- **Weights:** Open weights
- **Reasoning:** No
- **Context window:** 131K
- **Max output:** 4K
- **Input price:** $0.04 / M
- **Output price:** $0.08 / M
- **Blended price:** $0.05 / M
- **Output speed:** 72 tokens/s [Kagi](https://help.kagi.com/kagi/ai/llm-benchmark.html)
- **Value:** #4 of 219
- **Knowledge cutoff:** August 2024
- **Input:** text, image
- **Hugging Face:** [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it)

## Category scores

Each category score combines every public result we have in that category.

Gemma 3 4B category scores

1.  Coding 35.9
2.  Agentic & Tool Use 20.9
3.  Reasoning 13.2
4.  Math 16.8
5.  Knowledge 11.8
6.  Multilingual 42.5
7.  Instruction Following 65.2
8.  Long Context 38.7
9.  Writing & Preference 42.0
10.  020406080

Gemma 3 4B category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 35.9 | #215 | 1 |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 20.9 | #142 | 1 |
| [Reasoning](https://noometry.com/best/reasoning) | 13.2 | #335 | 5 |
| [Math](https://noometry.com/best/math) | 16.8 | #292 | 2 |
| [Knowledge](https://noometry.com/best/knowledge) | 11.8 | #299 | 3 |
| [Multilingual](https://noometry.com/best/multilingual) | 42.5 | #194 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 65.2 | #225 | 1 |
| [Long Context](https://noometry.com/best/long-context) | 38.7 | #194 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 42.0 | #239 | 4 |

## Strengths and weaknesses

Categories where Gemma 3 4B places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

Gemma 3 4B: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 35.9 | −2.9 | #215 of 340, top 64% |
| [Multilingual](https://noometry.com/best/multilingual) | 42.5 | −4.9 | #194 of 297, top 66% |
| [Long Context](https://noometry.com/best/long-context) | 38.7 | −2.3 | #194 of 296, top 66% |

### Weakest categories

Gemma 3 4B: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 13.2 | −10.4 | #335 of 350, top 96% |
| [Knowledge](https://noometry.com/best/knowledge) | 11.8 | −25.5 | #299 of 314, top 96% |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 20.9 | −9.5 | #142 of 154, top 93% |

## Closest competitors

The models ranked just above and below Gemma 3 4B. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Gemma 3 4B
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Qwen1.5 4b Chat](https://noometry.com/models/qwen1-5-4b-chat) | #322 | 28.8 | — | — | [Compare](https://noometry.com/compare/gemma-3-4b-vs-qwen1-5-4b-chat) |
| [Llama 3-70B](https://noometry.com/models/llama-3-70b) | #323 | 28.8 | — | 104 | [Compare](https://noometry.com/compare/gemma-3-4b-vs-llama-3-70b) |
| [GPT-4o](https://noometry.com/models/gpt-4o) | #324 | 28.6 | $4.38 | — | [Compare](https://noometry.com/compare/gemma-3-4b-vs-gpt-4o) |
| [Ministral 8B](https://noometry.com/models/ministral-8b) | #325 | 28.2 | $0.15 | — | [Compare](https://noometry.com/compare/gemma-3-4b-vs-ministral-8b) |
| [GPT-4.1 nano](https://noometry.com/models/gpt-4-1-nano) | #327 | 27.9 | $0.18 | 135 | [Compare](https://noometry.com/compare/gemma-3-4b-vs-gpt-4-1-nano) |
| [Phi 3 Mini 4k Instruct](https://noometry.com/models/phi-3-mini-4k-instruct) | #328 | 27.9 | — | — | [Compare](https://noometry.com/compare/gemma-3-4b-vs-phi-3-mini-4k-instruct) |
| [Yi-34B](https://noometry.com/models/yi-34b) | #329 | 27.8 | — | — | [Compare](https://noometry.com/compare/gemma-3-4b-vs-yi-34b) |
| [Llama 4 Scout](https://noometry.com/models/llama-4-scout) | #330 | 27.7 | $0.15 | 272 | [Compare](https://noometry.com/compare/gemma-3-4b-vs-llama-4-scout) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Coding

Gemma 3 4B Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1230 | #231 of 294, top 79% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Agentic & Tool Use

Gemma 3 4B Agentic & Tool Use benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Berkeley Function Calling Leaderboard](https://noometry.com/benchmarks/bfcl) | 19.6% | #45 of 49, top 92% | prompt | [Berkeley Function Calling Leaderboard](https://gorilla.cs.berkeley.edu/leaderboard.html) |  |

### Reasoning

Gemma 3 4B Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 25.2% | #96 of 99, top 97% |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 0% | #113 of 129, top 88% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-28 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1253 | #218 of 297, top 74% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 50.9% | #134 of 151, top 89% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 2.8% | #125 of 125, top 100% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 116.02 | #184 of 213, top 87% |  | [Epoch AI](https://epoch.ai/eci) | 2025-03-12 |

### Math

Gemma 3 4B Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 7.5% | #139 of 173, top 81% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-28 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1239 | #221 of 285, top 78% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Knowledge

Gemma 3 4B Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 23.2% | #183 of 186, top 99% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-28 |
| [Vectara Hallucination Rate](https://noometry.com/benchmarks/vectara-hallucination) (lower is better) | 6.4% | #24 of 96, top 25% |  | [Vectara Hallucination Leaderboard](https://github.com/vectara/hallucination-leaderboard) |  |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1223 | #212 of 273, top 78% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multilingual

Gemma 3 4B Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1273 | #194 of 297, top 66% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1281 | #160 of 231, top 70% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1294 | #180 of 283, top 64% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

Gemma 3 4B Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1239 | #223 of 298, top 75% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

Gemma 3 4B Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1273 | #208 of 291, top 72% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

Gemma 3 4B Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1291 | #196 of 297, top 66% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1271 | #188 of 295, top 64% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [EQ-Bench Creative Writing](https://noometry.com/benchmarks/eqbench-creative-writing) | 1068 | #94 of 115, top 82% |  | [EQ-Bench](https://eqbench.com/creative_writing.html) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1255 | #220 of 295, top 75% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## API pricing by provider

Gemma 3 4B API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) | $0.04 | $0.08 | — | 2026-10-10 |
| [deepinfra](https://deepinfra.com/models) | $0.05 | $0.10 | — | 2026-10-10 |
| [openrouter](https://openrouter.ai/google/gemma-3-4b-it) | $0.05 | $0.10 | — | 2026-10-10 |

[All Google API prices →](https://noometry.com/llm-pricing/google) [Estimate your cost →](https://noometry.com/tools/cost-calculator)

## Compare Gemma 3 4B

-   [Gemma 3 4B vs Gemma 3 27B](https://noometry.com/compare/gemma-3-27b-vs-gemma-3-4b)
-   [Gemma 3 4B vs Ministral 8B](https://noometry.com/compare/gemma-3-4b-vs-ministral-8b)
-   [Gemma 3 4B vs GPT-4.1 nano](https://noometry.com/compare/gemma-3-4b-vs-gpt-4-1-nano)
-   [Gemma 3 4B vs GPT-4o](https://noometry.com/compare/gemma-3-4b-vs-gpt-4o)
-   [Gemma 3 4B vs Phi 3 Mini 4k Instruct](https://noometry.com/compare/gemma-3-4b-vs-phi-3-mini-4k-instruct)
-   [Gemma 3 4B vs Llama 3-70B](https://noometry.com/compare/gemma-3-4b-vs-llama-3-70b)
-   [Gemma 3 4B vs Yi-34B](https://noometry.com/compare/gemma-3-4b-vs-yi-34b)
-   [Gemma 3 4B vs GPT-6 Astra](https://noometry.com/compare/gemma-3-4b-vs-gpt-6-astra)
-   [Gemma 3 4B vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-gemma-3-4b)
-   [Gemma 3 4B vs Kimi K3](https://noometry.com/compare/gemma-3-4b-vs-kimi-k3)
-   [Gemma 3 4B vs Grok 4.6](https://noometry.com/compare/gemma-3-4b-vs-grok-4-6)
-   [Gemma 3 4B vs Qwen3.8 Max](https://noometry.com/compare/gemma-3-4b-vs-qwen3-8-max)
-   [Gemma 3 4B vs GLM-5.3](https://noometry.com/compare/gemma-3-4b-vs-glm-5-3)
-   [Gemma 3 4B vs Muse Spark 1.3](https://noometry.com/compare/gemma-3-4b-vs-muse-spark-1-3)

## Other Google models

-   [Gemini 3.8 Flash](https://noometry.com/models/gemini-3-8-flash)61.8
-   [Gemini 3.7 Flash](https://noometry.com/models/gemini-3-7-flash)59.8
-   [Gemini 3.1 Pro Preview](https://noometry.com/models/gemini-3-1-pro-preview)56.7
-   [Gemini 4 Argon](https://noometry.com/models/gemini-4-argon)56.5
-   [Gemini 3 Pro](https://noometry.com/models/gemini-3-pro)54.8
-   [Gemini 3.5 Flash](https://noometry.com/models/gemini-3-5-flash)54.2
-   [Gemini 3.6 Flash](https://noometry.com/models/gemini-3-6-flash)54.1
-   [Gemini 3 Flash Preview](https://noometry.com/models/gemini-3-flash-preview)52.3

## Frequently asked questions

### How good is Gemma 3 4B?

Gemma 3 4B by Google ranks 326th of 354 ranked models on the Noometry Index as of October 2026, with a score of 28.1. Its strongest category is agentic & tool use, where it ranks 142nd. API pricing starts at $0.04 per million input tokens and $0.08 per million output tokens, with a 131K-token context window.

### How much does Gemma 3 4B cost?

Gemma 3 4B costs $0.04 per million input tokens and $0.08 per million output tokens on bedrock.

### What is Gemma 3 4B's context window?

Gemma 3 4B accepts up to 131K tokens of input and can write up to 4K tokens in one response.

### Is Gemma 3 4B open source?

Yes. Gemma 3 4B's weights are downloadable from Hugging Face (google/gemma-3-4b-it); check the license for commercial terms.

### How fast is Gemma 3 4B?

Gemma 3 4B generated about 72 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

### What are Gemma 3 4B's strengths and weaknesses?

Relative to other ranked models, Gemma 3 4B places best in coding, multilingual, long context and lowest in reasoning, knowledge, agentic & tool use.

### What is Gemma 3 4B best at?

Its best category is agentic & tool use, where it ranks 142nd on Noometry.

### Cite this page

Noometry. (2026). Gemma 3 4B benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/gemma-3-4b

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/gemma-3-4b.md).