Google, open weights

# Gemma 4 31B IT

> Gemma 4 31B IT by Google, released April 2026. Ranked #90 of 354 with a Noometry Index of 43.5. API: $0.09 in / $0.34 out per M tokens. 262K context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/gemma-4-31b-it
- Last updated: 2026-10-10
- Title: Gemma 4 31B IT Benchmarks, Price & Rank (October 2026)

Gemma 4 31B IT by Google ranks 90th of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.5. Its strongest category is multimodal, where it ranks 34th. API pricing starts at $0.09 per million input tokens and $0.34 per million output tokens, with a 262K-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #90 of 354
- **Index score:** 43.5
- **Evidence:** Confirmed 35 results
- **Provider:** [![](/logos/google.svg) Google](https://noometry.com/providers/google)
- **Released:** April 2, 2026
- **Weights:** Open weights
- **Reasoning:** Yes
- **Context window:** 262K
- **Max output:** 33K
- **Input price:** $0.09 / M
- **Output price:** $0.34 / M
- **Blended price:** $0.15 / M
- **Output speed:** 3 tokens/s [Kagi](https://help.kagi.com/kagi/ai/llm-benchmark.html)
- **Value:** #22 of 219
- **Knowledge cutoff:** Unknown
- **Input:** text, image
- **Hugging Face:** [google/gemma-4-31B-it](https://huggingface.co/google/gemma-4-31B-it)

## Category scores

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

Gemma 4 31B IT category scores

1.  Coding 42.3
2.  Reasoning 27.2
3.  Math 43.2
4.  Knowledge 37.9
5.  Multimodal 41.6
6.  Multilingual 53.8
7.  Instruction Following 75.5
8.  Long Context 44.2
9.  Writing & Preference 60.5
10.  020406080

Gemma 4 31B IT category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 42.3 | #108 | 4 |
| [Reasoning](https://noometry.com/best/reasoning) | 27.2 | #122 | 9 |
| [Math](https://noometry.com/best/math) | 43.2 | #81 | 2 |
| [Knowledge](https://noometry.com/best/knowledge) | 37.9 | #151 | 4 |
| [Multimodal](https://noometry.com/best/multimodal) | 41.6 | #34 | 1 |
| [Multilingual](https://noometry.com/best/multilingual) | 53.8 | #57 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 75.5 | #61 | 1 |
| [Long Context](https://noometry.com/best/long-context) | 44.2 | #71 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 60.5 | #96 | 5 |

## Strengths and weaknesses

Categories where Gemma 4 31B IT places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

Gemma 4 31B IT: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Multilingual](https://noometry.com/best/multilingual) | 53.8 | +6.4 | #57 of 297, top 20% |
| [Instruction Following](https://noometry.com/best/instruction-following) | 75.5 | +4.2 | #61 of 305, top 20% |
| [Long Context](https://noometry.com/best/long-context) | 44.2 | +3.3 | #71 of 296, top 24% |

### Weakest categories

Gemma 4 31B IT: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Knowledge](https://noometry.com/best/knowledge) | 37.9 | +0.6 | #151 of 314, top 49% |
| [Reasoning](https://noometry.com/best/reasoning) | 27.2 | +3.6 | #122 of 350, top 35% |
| [Coding](https://noometry.com/best/coding) | 42.3 | +3.6 | #108 of 340, top 32% |

## Closest competitors

The models ranked just above and below Gemma 4 31B IT. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Gemma 4 31B IT
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Grok 4.3](https://noometry.com/models/grok-4-3) | #86 | 43.8 | $1.56 | — | [Compare](https://noometry.com/compare/gemma-4-31b-it-vs-grok-4-3) |
| [Qwen3 Max](https://noometry.com/models/qwen3-max) | #87 | 43.7 | $2.40 | 48 | [Compare](https://noometry.com/compare/gemma-4-31b-it-vs-qwen3-max) |
| [MiMo-V2-Omni](https://noometry.com/models/mimo-v2-omni) | #88 | 43.6 | $0.18 | — | [Compare](https://noometry.com/compare/gemma-4-31b-it-vs-mimo-v2-omni) |
| [Kimi K2.5 Instant](https://noometry.com/models/kimi-k2-5-instant) | #89 | 43.6 | — | — | [Compare](https://noometry.com/compare/gemma-4-31b-it-vs-kimi-k2-5-instant) |
| [Qwen3 235B-A22B](https://noometry.com/models/qwen3-235b-a22b) | #91 | 43.5 | $1.22 | 85 | [Compare](https://noometry.com/compare/gemma-4-31b-it-vs-qwen3-235b-a22b) |
| [Gemma 4 26B A4B IT](https://noometry.com/models/gemma-4-26b-a4b-it) | #92 | 43.5 | $0.11 | — | [Compare](https://noometry.com/compare/gemma-4-26b-a4b-it-vs-gemma-4-31b-it) |
| [MiMo-V2.5](https://noometry.com/models/mimo-v2-5) | #93 | 43.4 | $0.18 | — | [Compare](https://noometry.com/compare/gemma-4-31b-it-vs-mimo-v2-5) |
| [Kimi K2.7 Code](https://noometry.com/models/kimi-k2-7-code) | #94 | 43.3 | $1.71 | — | [Compare](https://noometry.com/compare/gemma-4-31b-it-vs-kimi-k2-7-code) |

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 4 31B IT Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena WebDev](https://noometry.com/benchmarks/arena-webdev) | 1366 | #82 of 113, top 73% |  | [LMArena](https://lmarena.ai/leaderboard/webdev) | 2026-10-08 |
| [SciCode](https://noometry.com/benchmarks/scicode) | 43.4% | #63 of 121, top 53% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 52.3% | #45 of 119, top 38% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1459 | #72 of 294, top 25% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [ALE-Bench](https://noometry.com/benchmarks/ale-bench) | 925.5 | #48 of 105, top 46% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Reasoning

Gemma 4 31B IT Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 63.5% | #35 of 99, top 36% |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |
| [NYT Connections (extended)](https://noometry.com/benchmarks/nyt-connections) | 15.7% |  |  | [Lech Mazur benchmarks](https://github.com/lechmazur/nyt-connections) |  |
| [NYT Connections (extended)](https://noometry.com/benchmarks/nyt-connections) | 70.6% | #48 of 91, top 53% |  | [Lech Mazur benchmarks](https://github.com/lechmazur/nyt-connections) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 1.4% | #75 of 134, top 56% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 5% | #93 of 129, top 73% | minimal | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-06 |
| [Thematic Generalization](https://noometry.com/benchmarks/thematic-generalization) | 53% | #15 of 23, top 66% |  | [Lech Mazur benchmarks](https://github.com/lechmazur/generalization) |  |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1448 | #67 of 297, top 23% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 82.7% | #62 of 151, top 42% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 39.3% | #47 of 125, top 38% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Surface Evolver Bench](https://noometry.com/benchmarks/surface-evolver-bench) | 30.6% | #21 of 25, top 84% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 142.74 | #94 of 213, top 45% |  | [Epoch AI](https://epoch.ai/eci) | 2026-04-02 |

### Math

Gemma 4 31B IT Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 73.3% | #85 of 173, top 50% | minimal | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-06 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1465 | #48 of 285, top 17% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Knowledge

Gemma 4 31B IT Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 75.8% | #91 of 186, top 49% | minimal | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-06 |
| [SimpleQA Verified](https://noometry.com/benchmarks/simpleqa-verified) | 10.4% | #75 of 77, top 98% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [Vectara Hallucination Rate](https://noometry.com/benchmarks/vectara-hallucination) (lower is better) | 7.4% | #32 of 96, top 34% |  | [Vectara Hallucination Leaderboard](https://github.com/vectara/hallucination-leaderboard) |  |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1465 | #56 of 273, top 21% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multimodal

Gemma 4 31B IT Multimodal benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Vision](https://noometry.com/benchmarks/arena-vision) | 1277 | #31 of 122, top 26% |  | [LMArena](https://lmarena.ai/leaderboard/vision) | 2026-10-09 |
| [LMArena Document](https://noometry.com/benchmarks/arena-document) | 1425 | #30 of 38, top 79% |  | [LMArena](https://lmarena.ai/leaderboard/document) | 2026-09-13 |

### Multilingual

Gemma 4 31B IT Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1431 | #57 of 297, top 20% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1476 | #70 of 285, top 25% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1435 | #86 of 223, top 39% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1460 | #33 of 283, top 12% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1444 | #61 of 226, top 27% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

Gemma 4 31B IT Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1433 | #57 of 298, top 20% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

Gemma 4 31B IT Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1446 | #56 of 291, top 20% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

Gemma 4 31B IT Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1443 | #55 of 297, top 19% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1415 | #59 of 295, top 20% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [EQ-Bench Creative Writing](https://noometry.com/benchmarks/eqbench-creative-writing) | 1368 | #72 of 115, top 63% |  | [EQ-Bench](https://eqbench.com/creative_writing.html) |  |
| [EQ-Bench 4](https://noometry.com/benchmarks/eqbench-4) | 1120 | #22 of 28, top 79% |  | [EQ-Bench](https://eqbench.com/) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1452 | #51 of 295, top 18% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## API pricing by provider

Gemma 4 31B IT API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) | $0.14 | $0.40 | — | 2026-10-10 |
| [deepinfra](https://deepinfra.com/models) | $0.20 | $0.40 | — | 2026-10-10 |
| [openrouter](https://openrouter.ai/google/gemma-4-31b-it) | $0.09 | $0.34 | $0.05 | 2026-10-10 |

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

## Compare Gemma 4 31B IT

-   [Gemma 4 31B IT vs Kimi K2.5 Instant](https://noometry.com/compare/gemma-4-31b-it-vs-kimi-k2-5-instant)
-   [Gemma 4 31B IT vs Qwen3 235B-A22B](https://noometry.com/compare/gemma-4-31b-it-vs-qwen3-235b-a22b)
-   [Gemma 4 31B IT vs MiMo-V2-Omni](https://noometry.com/compare/gemma-4-31b-it-vs-mimo-v2-omni)
-   [Gemma 4 31B IT vs Gemma 4 26B A4B IT](https://noometry.com/compare/gemma-4-26b-a4b-it-vs-gemma-4-31b-it)
-   [Gemma 4 31B IT vs Qwen3 Max](https://noometry.com/compare/gemma-4-31b-it-vs-qwen3-max)
-   [Gemma 4 31B IT vs MiMo-V2.5](https://noometry.com/compare/gemma-4-31b-it-vs-mimo-v2-5)
-   [Gemma 4 31B IT vs GPT-6 Astra](https://noometry.com/compare/gemma-4-31b-it-vs-gpt-6-astra)
-   [Gemma 4 31B IT vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-gemma-4-31b-it)
-   [Gemma 4 31B IT vs Kimi K3](https://noometry.com/compare/gemma-4-31b-it-vs-kimi-k3)
-   [Gemma 4 31B IT vs Grok 4.6](https://noometry.com/compare/gemma-4-31b-it-vs-grok-4-6)
-   [Gemma 4 31B IT vs Qwen3.8 Max](https://noometry.com/compare/gemma-4-31b-it-vs-qwen3-8-max)
-   [Gemma 4 31B IT vs GLM-5.3](https://noometry.com/compare/gemma-4-31b-it-vs-glm-5-3)
-   [Gemma 4 31B IT vs Muse Spark 1.3](https://noometry.com/compare/gemma-4-31b-it-vs-muse-spark-1-3)
-   [Gemma 4 31B IT vs DeepSeek V4 Pro](https://noometry.com/compare/deepseek-v4-pro-vs-gemma-4-31b-it)

## 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 4 31B IT?

Gemma 4 31B IT by Google ranks 90th of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.5. Its strongest category is multimodal, where it ranks 34th. API pricing starts at $0.09 per million input tokens and $0.34 per million output tokens, with a 262K-token context window.

### How much does Gemma 4 31B IT cost?

Gemma 4 31B IT costs $0.09 per million input tokens and $0.34 per million output tokens on openrouter, with cached input at $0.05.

### What is Gemma 4 31B IT's context window?

Gemma 4 31B IT accepts up to 262K tokens of input and can write up to 33K tokens in one response.

### Is Gemma 4 31B IT open source?

Yes. Gemma 4 31B IT's weights are downloadable from Hugging Face (google/gemma-4-31B-it); check the license for commercial terms.

### How fast is Gemma 4 31B IT?

Gemma 4 31B IT generated about 3 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

### What are Gemma 4 31B IT's strengths and weaknesses?

Relative to other ranked models, Gemma 4 31B IT places best in multilingual, instruction following, long context and lowest in knowledge, reasoning, coding.

### What is Gemma 4 31B IT best at?

Its best category is multimodal, where it ranks 34th on Noometry.

### Cite this page

Noometry. (2026). Gemma 4 31B IT benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/gemma-4-31b-it

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/gemma-4-31b-it.md).