# Grok 4.20 (Non-Reasoning) vs Llama 4 Scout

> Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 27.4 on the Noometry Index. Llama 4 Scout costs 10× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/grok-4-20-vs-llama-4-scout
- Last updated: 2026-10-10
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 10 categories and Llama 4 Scout in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.2 to 9.2.
- The biggest single-benchmark swing is ARC-AGI-1: 89.5% for Grok 4.20 (Non-Reasoning) and 0.5% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 128K.
- Llama 4 Scout has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.20 (Non-Reasoning) | Llama 4 Scout |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 48.5 | 27.4 |
| Rank | 48 | 323 |
| Context | 1M | 128K |
| Input $/M | $1.25 | $0.10 |
| Output $/M | $2.50 | $0.30 |
| Weights | Proprietary | Open |

## Coding

- Grok 4.20 (Non-Reasoning): 41.8 (#104)
- Llama 4 Scout: 19.9 (#334)

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 4 Scout |
|---|---|---|
| LMArena Coding | 1458 | 1286 |
| SWE-bench Verified (bash only) | — | 9.1% |
| LMArena WebDev | 1374 | — |
| SciCode | — | 17% |
| WeirdML | 52.3% | — |
| BigCodeBench Complete | — | 43.1% |
| ALE-Bench | 1,150 | — |

## Agentic & Tool Use

- Grok 4.20 (Non-Reasoning): 34.3 (#43)
- Llama 4 Scout: 24.4 (#109)

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 4 Scout |
|---|---|---|
| Terminal-Bench | 57.3% | — |
| Berkeley Function Calling Leaderboard | — | 28.1% |
| τ²-bench Banking | 18% | — |
| LMArena Search | 1189 | — |
| Vending-Bench 2 | 4,663 | — |

## Reasoning

- Grok 4.20 (Non-Reasoning): 52.2 (#30)
- Llama 4 Scout: 9.2 (#339)

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 4 Scout |
|---|---|---|
| ARC-AGI-2 | 65.1% | 0% |
| Kagi LLM Benchmark | 75% | 36.9% |
| ARC-AGI-1 | 89.5% | 0.5% |
| LMArena Hard Prompts | 1451 | 1266 |
| DTBench | 90.1% | 57.9% |
| LMCA | 38.7% | 12% |
| Epoch Capabilities Index | 152.01 | 129.64 |
| ForecastBench | 61.4 | 57.5 |
| NYT Connections (extended) | 85.4% | — |
| CritPt | — | 0% |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 63.8% | — |

## Math

- Grok 4.20 (Non-Reasoning): 48.0 (#54)
- Llama 4 Scout: 18.4 (#280)

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 92.2% | 7.8% |
| LMArena Math | 1455 | 1286 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 14% | — |
| Omni-MATH | — | 37.3% |
| MATH Level 5 | — | 62.3% |
| FrontierMath (Feb 2025 set) | — | 0% |

## Knowledge

- Grok 4.20 (Non-Reasoning): 52.8 (#54)
- Llama 4 Scout: 31.8 (#208)

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 89.3% | 51.8% |
| LMArena Expert | 1440 | 1236 |
| SimpleQA Verified | 30.2% | — |
| MMLU-Pro | — | 74.2% |
| Vectara Hallucination Rate | — | 7.7% |
| GPQA (HELM) | — | 50.7% |

## Multimodal

- Grok 4.20 (Non-Reasoning): 33.2 (#88)
- Llama 4 Scout: 31.6 (#98)

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 4 Scout |
|---|---|---|
| LMArena Vision | 1263 | 1118 |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |
| SpatialViz-Bench | — | 34.2% |

## Multilingual

- Grok 4.20 (Non-Reasoning): 54.7 (#38)
- Llama 4 Scout: 41.3 (#207)

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1440 | 1253 |
| LMArena Chinese | 1481 | 1256 |
| LMArena French | 1477 | 1283 |
| LMArena German | 1463 | 1274 |
| LMArena Japanese | 1450 | 1209 |
| LMArena Korean | 1417 | 1207 |
| LMArena Russian | 1457 | 1263 |
| LMArena Spanish | 1442 | 1277 |

## Instruction Following

- Grok 4.20 (Non-Reasoning): 75.0 (#79)
- Llama 4 Scout: 66.0 (#212)

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1420 | 1248 |
| IFEval | — | 81.8% |

## Long Context

- Grok 4.20 (Non-Reasoning): 45.4 (#33)
- Llama 4 Scout: 27.5 (#289)

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1436 | 1265 |
| Fiction.LiveBench | — | 36% |
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |

## Writing & Preference

- Grok 4.20 (Non-Reasoning): 65.9 (#42)
- Llama 4 Scout: 37.1 (#256)

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1451 | 1279 |
| LMArena Creative Writing | 1439 | 1249 |
| EQ-Bench Creative Writing | 1574 | 783 |
| LMArena Multi-Turn | 1456 | 1281 |
| WildBench | — | 78% |

## FAQ

### Is Grok 4.20 (Non-Reasoning) better than Llama 4 Scout?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 27.4 on the Noometry Index. Llama 4 Scout costs 10× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

### Which is cheaper, Grok 4.20 (Non-Reasoning) or Llama 4 Scout?

Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

### Is Grok 4.20 (Non-Reasoning) or Llama 4 Scout better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 19.9 in the Noometry coding category.

### Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 128K.

### How many benchmarks do Grok 4.20 (Non-Reasoning) and Llama 4 Scout share?

28 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Llama 4 Scout has 43.