# Grok 4.20 Multi-Agent vs Step 5 Preview

> Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 43.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-4-20-multi-agent-vs-step-5-preview
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Step 5 Preview leads 50.6 to 42.4.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 Multi-Agent.
- Step 5 Preview accepts more context: 1.02M tokens versus 1M.

## Snapshot

| | Grok 4.20 Multi-Agent | Step 5 Preview |
|---|---|---|
| Provider | xAI | StepFun |
| Noometry Index | 45.5 | 43.8 |
| Rank | 62 | 78 |
| Context | 1M | 1.02M |
| Input $/M | $1.25 | $1 |
| Output $/M | $2.50 | $2.70 |
| Weights | Proprietary | Proprietary |

## Coding

- Grok 4.20 Multi-Agent: 42.4 (#91)
- Step 5 Preview: 50.6 (#40)

| Benchmark | Grok 4.20 Multi-Agent | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1569 |
| SciCode | — | 58.9% |
| LMArena Coding | 1458 | — |

## Agentic & Tool Use

- Grok 4.20 Multi-Agent: —
- Step 5 Preview: —

| Benchmark | Grok 4.20 Multi-Agent | Step 5 Preview |
|---|---|---|
| LMArena Search | 1204 | — |

## Reasoning

- Grok 4.20 Multi-Agent: 42.4 (#44)
- Step 5 Preview: 38.0 (#58)

| Benchmark | Grok 4.20 Multi-Agent | Step 5 Preview |
|---|---|---|
| NYT Connections (extended) | 89.6% | — |
| CritPt | — | 20.9% |
| LMArena Hard Prompts | 1448 | — |

## Math

- Grok 4.20 Multi-Agent: 36.6 (#106)
- Step 5 Preview: —

| Benchmark | Grok 4.20 Multi-Agent | Step 5 Preview |
|---|---|---|
| LMArena Math | 1441 | — |

## Knowledge

- Grok 4.20 Multi-Agent: 39.7 (#116)
- Step 5 Preview: —

| Benchmark | Grok 4.20 Multi-Agent | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1445 | — |

## Multimodal

- Grok 4.20 Multi-Agent: 39.8 (#44)
- Step 5 Preview: —

| Benchmark | Grok 4.20 Multi-Agent | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1259 | — |

## Multilingual

- Grok 4.20 Multi-Agent: 54.6 (#40)
- Step 5 Preview: —

| Benchmark | Grok 4.20 Multi-Agent | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1440 | — |
| LMArena Chinese | 1475 | — |
| LMArena French | 1467 | — |
| LMArena German | 1456 | — |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1416 | — |
| LMArena Russian | 1457 | — |
| LMArena Spanish | 1447 | — |

## Instruction Following

- Grok 4.20 Multi-Agent: 75.0 (#80)
- Step 5 Preview: —

| Benchmark | Grok 4.20 Multi-Agent | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1420 | — |

## Long Context

- Grok 4.20 Multi-Agent: 43.7 (#84)
- Step 5 Preview: —

| Benchmark | Grok 4.20 Multi-Agent | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1430 | — |

## Writing & Preference

- Grok 4.20 Multi-Agent: 64.1 (#57)
- Step 5 Preview: —

| Benchmark | Grok 4.20 Multi-Agent | Step 5 Preview |
|---|---|---|
| LMArena Text | 1450 | — |
| LMArena Creative Writing | 1435 | — |
| LMArena Multi-Turn | 1451 | — |

## FAQ

### Is Grok 4.20 Multi-Agent better than Step 5 Preview?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 43.8 on the Noometry Index.

### Which is cheaper, Grok 4.20 Multi-Agent or Step 5 Preview?

Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; Grok 4.20 Multi-Agent lists at $1.25 and $2.50.

### Is Grok 4.20 Multi-Agent or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 50.6 versus 42.4 in the Noometry coding category.

### Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 1M.

### How many benchmarks do Grok 4.20 Multi-Agent and Step 5 Preview share?

0 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and Step 5 Preview has 3.