xAI, proprietary

# Grok-3 mini

> Grok-3 mini by xAI, released April 2025. Ranked #141 of 354 with a Noometry Index of 41.2. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/grok-3-mini
- Last updated: 2026-10-10
- Title: Grok-3 mini Benchmarks, Price & Rank (October 2026)

Grok-3 mini by xAI ranks 141st of 354 ranked models on the Noometry Index as of October 2026, with a score of 41.2. Its strongest category is instruction following, where it ranks 9th.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #141 of 354
- **Index score:** 41.2
- **Evidence:** Confirmed 35 results
- **Provider:** [xAI](https://noometry.com/providers/xai)
- **Released:** April 9, 2025
- **Weights:** Proprietary
- **Reasoning:** Unknown
- **Context window:** —
- **Max output:** —
- **Input price:** Not listed
- **Output price:** Not listed
- **Blended price:** Not listed
- **Output speed:** 10 tokens/s [Kagi](https://help.kagi.com/kagi/ai/llm-benchmark.html)
- **Value:** Not ranked
- **Knowledge cutoff:** Unknown

## Category scores

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

Grok-3 mini category scores

1.  Coding 40.8
2.  Reasoning 13.6
3.  Math 42.1
4.  Knowledge 46.4
5.  Multilingual 48.1
6.  Instruction Following 78.5
7.  Long Context 41.0
8.  Writing & Preference 52.5
9.  020406080

Grok-3 mini category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 40.8 | #131 | 3 |
| [Reasoning](https://noometry.com/best/reasoning) | 13.6 | #334 | 4 |
| [Math](https://noometry.com/best/math) | 42.1 | #85 | 4 |
| [Knowledge](https://noometry.com/best/knowledge) | 46.4 | #81 | 5 |
| [Multilingual](https://noometry.com/best/multilingual) | 48.1 | #145 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 78.5 | #9 | 2 |
| [Long Context](https://noometry.com/best/long-context) | 41.0 | #147 | 2 |
| [Writing & Preference](https://noometry.com/best/writing) | 52.5 | #169 | 5 |

## Strengths and weaknesses

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

### Strongest categories

Grok-3 mini: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Instruction Following](https://noometry.com/best/instruction-following) | 78.5 | +7.3 | #9 of 305, top 3% |
| [Knowledge](https://noometry.com/best/knowledge) | 46.4 | +9.1 | #81 of 314, top 26% |
| [Math](https://noometry.com/best/math) | 42.1 | +5.5 | #85 of 327, top 26% |

### Weakest categories

Grok-3 mini: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 13.6 | −10.0 | #334 of 350, top 96% |
| [Writing & Preference](https://noometry.com/best/writing) | 52.5 | −1.3 | #169 of 312, top 55% |
| [Long Context](https://noometry.com/best/long-context) | 41.0 | +0.1 | #147 of 296, top 50% |

## Closest competitors

The models ranked just above and below Grok-3 mini. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Grok-3 mini
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [GLM-4.6V](https://noometry.com/models/glm-4-6v) | #137 | 41.3 | $0.45 | — | [Compare](https://noometry.com/compare/glm-4-6v-vs-grok-3-mini) |
| [MiMo-V2-Flash](https://noometry.com/models/mimo-v2-flash) | #138 | 41.3 | $0.18 | — | [Compare](https://noometry.com/compare/grok-3-mini-vs-mimo-v2-flash) |
| [Hunyuan Turbos 20250226](https://noometry.com/models/hunyuan-turbos) | #139 | 41.3 | — | — | [Compare](https://noometry.com/compare/grok-3-mini-vs-hunyuan-turbos) |
| [Kimi K2 (Jul 2025)](https://noometry.com/models/kimi-k2) | #140 | 41.2 | $1 | 201 | [Compare](https://noometry.com/compare/grok-3-mini-vs-kimi-k2) |
| [Claude Opus 4.1](https://noometry.com/models/claude-opus-4-1) | #142 | 41.0 | $30 | — | [Compare](https://noometry.com/compare/claude-opus-4-1-vs-grok-3-mini) |
| [o1](https://noometry.com/models/o1) | #143 | 40.9 | $26.25 | — | [Compare](https://noometry.com/compare/grok-3-mini-vs-o1) |
| [Gemini 3.1 Flash Lite](https://noometry.com/models/gemini-3-1-flash-lite) | #144 | 40.8 | $0.56 | 10 | [Compare](https://noometry.com/compare/gemini-3-1-flash-lite-vs-grok-3-mini) |
| [Claude Sonnet 4](https://noometry.com/models/claude-sonnet-4) | #145 | 40.8 | $6 | 31 | [Compare](https://noometry.com/compare/claude-sonnet-4-vs-grok-3-mini) |

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

Grok-3 mini Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) | 49.3% | #23 of 44, top 53% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) | 34.7% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 42.6% | #69 of 119, top 58% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 42.6% | #69 of 119, top 58% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1367 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1379 | #151 of 294, top 52% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Reasoning

Grok-3 mini Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 0.4% | #74 of 83, top 90% | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 61.3% | #41 of 99, top 42% |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 16.5% | #70 of 83, top 85% | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 16.5% | #70 of 83, top 85% | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1364 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1375 | #141 of 297, top 48% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 140.35 | #106 of 213, top 50% |  | [Epoch AI](https://epoch.ai/eci) | 2025-06-24 |

### Math

Grok-3 mini Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 77.8% | #83 of 173, top 48% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-04-10 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 62.2% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2025-04-10 |
| [Omni-MATH](https://noometry.com/benchmarks/omni-math) | 31.8% | #36 of 57, top 64% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1372 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1386 | #142 of 285, top 50% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 88.1% |  | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-04-10 |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 90.9% | #14 of 79, top 18% | low | [Epoch AI](https://epoch.ai/benchmarks) | 2025-04-10 |
| [FrontierMath (Feb 2025 set)](https://noometry.com/benchmarks/frontiermath-2025-02) | 5.9% | #44 of 68, top 65% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-04-10 |
| [FrontierMath (Feb 2025 set)](https://noometry.com/benchmarks/frontiermath-2025-02) | 2.8% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2025-04-10 |

### Knowledge

Grok-3 mini Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 75.5% |  | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-05-26 |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 76.3% | #90 of 186, top 49% | low | [Epoch AI](https://epoch.ai/benchmarks) | 2025-04-10 |
| [MMLU-Pro](https://noometry.com/benchmarks/mmlu-pro) | 79.9% | #16 of 58, top 28% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [Confabulations](https://noometry.com/benchmarks/confabulations) (lower is better) | 10.8% | #3 of 51, top 6% | high | [Lech Mazur benchmarks](https://github.com/lechmazur/confabulations) |  |
| [GPQA (HELM)](https://noometry.com/benchmarks/helm-gpqa) | 67.5% | #14 of 57, top 25% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1366 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1395 | #129 of 273, top 48% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multilingual

Grok-3 mini Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1349 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1352 | #145 of 297, top 49% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1377 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1387 | #144 of 285, top 51% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1357 | #143 of 223, top 65% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1347 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1347 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1349 | #132 of 231, top 58% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1342 | #103 of 211, top 49% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1317 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1306 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1335 | #112 of 213, top 53% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1353 | #145 of 283, top 52% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1351 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1381 | #126 of 226, top 56% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1359 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

Grok-3 mini Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [IFEval](https://noometry.com/benchmarks/ifeval) | 95.1% | Best of 57 |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1346 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1357 | #140 of 298, top 47% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

Grok-3 mini Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Fiction.LiveBench](https://noometry.com/benchmarks/fiction-livebench) | 66.7% | #20 of 47, top 43% | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1357 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1372 | #138 of 291, top 48% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

Grok-3 mini Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1364 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1370 | #144 of 297, top 49% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1342 | #137 of 295, top 47% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1335 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [Short-Story Creative Writing](https://noometry.com/benchmarks/lech-mazur-writing) | 73.5% | #28 of 39, top 72% | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WildBench](https://noometry.com/benchmarks/wildbench) | 65.1% | #57 of 57, top 100% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1351 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1355 | #151 of 295, top 52% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## Compare Grok-3 mini

-   [Grok-3 mini vs Grok 2 Mini 2024 08 13](https://noometry.com/compare/grok-2-mini-vs-grok-3-mini)
-   [Grok-3 mini vs Kimi K2 (Jul 2025)](https://noometry.com/compare/grok-3-mini-vs-kimi-k2)
-   [Grok-3 mini vs Claude Opus 4.1](https://noometry.com/compare/claude-opus-4-1-vs-grok-3-mini)
-   [Grok-3 mini vs Hunyuan Turbos 20250226](https://noometry.com/compare/grok-3-mini-vs-hunyuan-turbos)
-   [Grok-3 mini vs o1](https://noometry.com/compare/grok-3-mini-vs-o1)
-   [Grok-3 mini vs MiMo-V2-Flash](https://noometry.com/compare/grok-3-mini-vs-mimo-v2-flash)
-   [Grok-3 mini vs Gemini 3.1 Flash Lite](https://noometry.com/compare/gemini-3-1-flash-lite-vs-grok-3-mini)
-   [Grok-3 mini vs GPT-6 Astra](https://noometry.com/compare/gpt-6-astra-vs-grok-3-mini)
-   [Grok-3 mini vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-grok-3-mini)
-   [Grok-3 mini vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-grok-3-mini)
-   [Grok-3 mini vs Kimi K3](https://noometry.com/compare/grok-3-mini-vs-kimi-k3)
-   [Grok-3 mini vs Qwen3.8 Max](https://noometry.com/compare/grok-3-mini-vs-qwen3-8-max)
-   [Grok-3 mini vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-grok-3-mini)
-   [Grok-3 mini vs Muse Spark 1.3](https://noometry.com/compare/grok-3-mini-vs-muse-spark-1-3)

## Other xAI models

-   [Grok 4.6](https://noometry.com/models/grok-4-6)56.9
-   [Grok 4.5](https://noometry.com/models/grok-4-5)55.0
-   [Grok 4.7](https://noometry.com/models/grok-4-7)53.1
-   [Grok 4.20 (Non-Reasoning)](https://noometry.com/models/grok-4-20)48.6
-   [Grok 4](https://noometry.com/models/grok-4)48.1
-   [Grok 4.20 Multi-Agent](https://noometry.com/models/grok-4-20-multi-agent)46.2
-   [Grok 4.3](https://noometry.com/models/grok-4-3)43.8
-   [Grok 4.1](https://noometry.com/models/grok-4-1)41.5

## Frequently asked questions

### How good is Grok-3 mini?

Grok-3 mini by xAI ranks 141st of 354 ranked models on the Noometry Index as of October 2026, with a score of 41.2. Its strongest category is instruction following, where it ranks 9th.

### Is Grok-3 mini open source?

No. Grok-3 mini is proprietary and available only through xAI's API and partner platforms.

### How fast is Grok-3 mini?

Grok-3 mini generated about 10 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

### What are Grok-3 mini's strengths and weaknesses?

Relative to other ranked models, Grok-3 mini places best in instruction following, knowledge, math and lowest in reasoning, writing & preference, long context.

### What is Grok-3 mini best at?

Its best category is instruction following, where it ranks 9th on Noometry.

### Cite this page

Noometry. (2026). Grok-3 mini benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/grok-3-mini

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