xAI, proprietary

# Grok 4.20 Multi-Agent

> Grok 4.20 Multi-Agent by xAI, released March 2026. Ranked #65 of 354 with a Noometry Index of 46.2. API: $1.25 in / $2.50 out per M tokens. 1M context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/grok-4-20-multi-agent
- Last updated: 2026-10-10
- Title: Grok 4.20 Multi-Agent Benchmarks, Price & Rank (October 2026)

Grok 4.20 Multi-Agent by xAI ranks 65th of 354 ranked models on the Noometry Index as of October 2026, with a score of 46.2. Its strongest category is multilingual, where it ranks 43rd. API pricing starts at $1.25 per million input tokens and $2.50 per million output tokens, with a 1M-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #65 of 354
- **Index score:** 46.2
- **Evidence:** Confirmed 20 results
- **Provider:** [xAI](https://noometry.com/providers/xai)
- **Released:** March 9, 2026
- **Weights:** Proprietary
- **Reasoning:** Yes
- **Context window:** 1M
- **Max output:** 30K
- **Input price:** $1.25 / M
- **Output price:** $2.50 / M
- **Blended price:** $1.56 / M
- **Output speed:** Not measured
- **Value:** #135 of 219
- **Knowledge cutoff:** Unknown
- **Input:** text, image, pdf

## Category scores

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

Grok 4.20 Multi-Agent category scores

1.  Coding 43.0
2.  Reasoning 43.9
3.  Math 39.4
4.  Knowledge 40.4
5.  Multimodal 40.5
6.  Multilingual 54.4
7.  Instruction Following 74.8
8.  Long Context 43.7
9.  Writing & Preference 64.0
10.  304050607080

Grok 4.20 Multi-Agent category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 43.0 | #92 | 1 |
| [Reasoning](https://noometry.com/best/reasoning) | 43.9 | #48 | 2 |
| [Math](https://noometry.com/best/math) | 39.4 | #104 | 1 |
| [Knowledge](https://noometry.com/best/knowledge) | 40.4 | #119 | 1 |
| [Multimodal](https://noometry.com/best/multimodal) | 40.5 | #48 | 1 |
| [Multilingual](https://noometry.com/best/multilingual) | 54.4 | #43 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 74.8 | #84 | 1 |
| [Long Context](https://noometry.com/best/long-context) | 43.7 | #88 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 64.0 | #59 | 3 |

## Strengths and weaknesses

Categories where Grok 4.20 Multi-Agent places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

Grok 4.20 Multi-Agent: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 43.9 | +20.3 | #48 of 350, top 14% |
| [Multilingual](https://noometry.com/best/multilingual) | 54.4 | +7.0 | #43 of 297, top 15% |
| [Writing & Preference](https://noometry.com/best/writing) | 64.0 | +10.2 | #59 of 312, top 19% |

### Weakest categories

Grok 4.20 Multi-Agent: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Knowledge](https://noometry.com/best/knowledge) | 40.4 | +3.0 | #119 of 314, top 38% |
| [Multimodal](https://noometry.com/best/multimodal) | 40.5 | +2.0 | #48 of 128, top 38% |
| [Math](https://noometry.com/best/math) | 39.4 | +2.8 | #104 of 327, top 32% |

## Closest competitors

The models ranked just above and below Grok 4.20 Multi-Agent. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Grok 4.20 Multi-Agent
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [o3](https://noometry.com/models/o3) | #61 | 47.5 | $3.50 | 3 | [Compare](https://noometry.com/compare/grok-4-20-multi-agent-vs-o3) |
| [Qwen3.6 Plus](https://noometry.com/models/qwen3-6-plus) | #62 | 47.5 | $1.13 | — | [Compare](https://noometry.com/compare/grok-4-20-multi-agent-vs-qwen3-6-plus) |
| [Inkling-Small](https://noometry.com/models/inkling-small) | #63 | 46.5 | $0.64 | — | [Compare](https://noometry.com/compare/grok-4-20-multi-agent-vs-inkling-small) |
| [GPT-5 Pro](https://noometry.com/models/gpt-5-pro) | #64 | 46.4 | $41.25 | 5 | [Compare](https://noometry.com/compare/gpt-5-pro-vs-grok-4-20-multi-agent) |
| [GLM-5](https://noometry.com/models/glm-5) | #66 | 46.1 | $1.55 | 23 | [Compare](https://noometry.com/compare/glm-5-vs-grok-4-20-multi-agent) |
| [Qwen3.5 397B-A17B](https://noometry.com/models/qwen3-5-397b-a17b) | #67 | 46.0 | $1.35 | 9 | [Compare](https://noometry.com/compare/grok-4-20-multi-agent-vs-qwen3-5-397b-a17b) |
| [Qwen3.8 27B](https://noometry.com/models/qwen3-8-27b) | #68 | 46.0 | $1.11 | — | [Compare](https://noometry.com/compare/grok-4-20-multi-agent-vs-qwen3-8-27b) |
| [GPT-5.3 Codex](https://noometry.com/models/gpt-5-3-codex) | #69 | 45.8 | $4.81 | — | [Compare](https://noometry.com/compare/gpt-5-3-codex-vs-grok-4-20-multi-agent) |

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 4.20 Multi-Agent Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1457 | #74 of 294, top 26% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Agentic & Tool Use

Grok 4.20 Multi-Agent Agentic & Tool Use benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Search](https://noometry.com/benchmarks/arena-search) | 1204 | #13 of 32, top 41% |  | [LMArena](https://lmarena.ai/leaderboard/search) | 2026-08-24 |

### Reasoning

Grok 4.20 Multi-Agent Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [NYT Connections (extended)](https://noometry.com/benchmarks/nyt-connections) | 89.6% | #21 of 91, top 24% |  | [Lech Mazur benchmarks](https://github.com/lechmazur/nyt-connections) |  |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1448 | #64 of 297, top 22% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Math

Grok 4.20 Multi-Agent Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1442 | #67 of 285, top 24% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Knowledge

Grok 4.20 Multi-Agent Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1445 | #75 of 273, top 28% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multimodal

Grok 4.20 Multi-Agent Multimodal benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Vision](https://noometry.com/benchmarks/arena-vision) | 1259 | #49 of 122, top 41% |  | [LMArena](https://lmarena.ai/leaderboard/vision) | 2026-10-09 |

### Multilingual

Grok 4.20 Multi-Agent Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1440 | #43 of 297, top 15% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1475 | #71 of 285, top 25% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1466 | #43 of 223, top 20% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1456 | #39 of 231, top 17% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1405 | #55 of 211, top 27% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1416 | #38 of 213, top 18% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1457 | #36 of 283, top 13% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1447 | #57 of 226, top 26% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

Grok 4.20 Multi-Agent Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1420 | #74 of 298, top 25% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

Grok 4.20 Multi-Agent Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1431 | #77 of 291, top 27% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

Grok 4.20 Multi-Agent Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1450 | #44 of 297, top 15% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1436 | #43 of 295, top 15% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1452 | #52 of 295, top 18% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## API pricing by provider

Grok 4.20 Multi-Agent API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [openrouter](https://openrouter.ai/x-ai/grok-4.20-multi-agent) | $1.25 | $2.50 | $0.20 | 2026-10-10 |
| [xai](https://docs.x.ai/docs/models) | $1.25 | $2.50 | $0.20 | 2026-10-10 |

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

## Compare Grok 4.20 Multi-Agent

-   [Grok 4.20 Multi-Agent vs GPT-5 Pro](https://noometry.com/compare/gpt-5-pro-vs-grok-4-20-multi-agent)
-   [Grok 4.20 Multi-Agent vs GLM-5](https://noometry.com/compare/glm-5-vs-grok-4-20-multi-agent)
-   [Grok 4.20 Multi-Agent vs Inkling-Small](https://noometry.com/compare/grok-4-20-multi-agent-vs-inkling-small)
-   [Grok 4.20 Multi-Agent vs Qwen3.5 397B-A17B](https://noometry.com/compare/grok-4-20-multi-agent-vs-qwen3-5-397b-a17b)
-   [Grok 4.20 Multi-Agent vs Qwen3.6 Plus](https://noometry.com/compare/grok-4-20-multi-agent-vs-qwen3-6-plus)
-   [Grok 4.20 Multi-Agent vs Qwen3.8 27B](https://noometry.com/compare/grok-4-20-multi-agent-vs-qwen3-8-27b)
-   [Grok 4.20 Multi-Agent vs GPT-6 Astra](https://noometry.com/compare/gpt-6-astra-vs-grok-4-20-multi-agent)
-   [Grok 4.20 Multi-Agent vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-grok-4-20-multi-agent)
-   [Grok 4.20 Multi-Agent vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-grok-4-20-multi-agent)
-   [Grok 4.20 Multi-Agent vs Kimi K3](https://noometry.com/compare/grok-4-20-multi-agent-vs-kimi-k3)
-   [Grok 4.20 Multi-Agent vs Qwen3.8 Max](https://noometry.com/compare/grok-4-20-multi-agent-vs-qwen3-8-max)
-   [Grok 4.20 Multi-Agent vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-grok-4-20-multi-agent)
-   [Grok 4.20 Multi-Agent vs Muse Spark 1.3](https://noometry.com/compare/grok-4-20-multi-agent-vs-muse-spark-1-3)
-   [Grok 4.20 Multi-Agent vs DeepSeek V4 Pro](https://noometry.com/compare/deepseek-v4-pro-vs-grok-4-20-multi-agent)

## 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 4.3](https://noometry.com/models/grok-4-3)43.8
-   [Grok 4.1](https://noometry.com/models/grok-4-1)41.5
-   [Grok 4.1 Fast](https://noometry.com/models/grok-4-1-fast)41.4

## Frequently asked questions

### How good is Grok 4.20 Multi-Agent?

Grok 4.20 Multi-Agent by xAI ranks 65th of 354 ranked models on the Noometry Index as of October 2026, with a score of 46.2. Its strongest category is multilingual, where it ranks 43rd. API pricing starts at $1.25 per million input tokens and $2.50 per million output tokens, with a 1M-token context window.

### How much does Grok 4.20 Multi-Agent cost?

Grok 4.20 Multi-Agent costs $1.25 per million input tokens and $2.50 per million output tokens on xAI's own API, with cached input at $0.20.

### What is Grok 4.20 Multi-Agent's context window?

Grok 4.20 Multi-Agent accepts up to 1M tokens of input and can write up to 30K tokens in one response.

### Is Grok 4.20 Multi-Agent open source?

No. Grok 4.20 Multi-Agent is proprietary and available only through xAI's API and partner platforms.

### What are Grok 4.20 Multi-Agent's strengths and weaknesses?

Relative to other ranked models, Grok 4.20 Multi-Agent places best in reasoning, multilingual, writing & preference and lowest in knowledge, multimodal, math.

### What is Grok 4.20 Multi-Agent best at?

Its best category is multilingual, where it ranks 43rd on Noometry.

### Cite this page

Noometry. (2026). Grok 4.20 Multi-Agent benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/grok-4-20-multi-agent

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/grok-4-20-multi-agent.md).