# Grok 4.20 (Non-Reasoning) vs Llama 13b

> Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 23.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-4-20-vs-llama-13b
- Last updated: 2026-10-10
- Shared benchmarks: 9

## Summary

- They share 9 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 6 categories and Llama 13b in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 4.20 (Non-Reasoning) leads 65.9 to 13.9.
- Llama 13b has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.20 (Non-Reasoning) | Llama 13b |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 48.5 | 23.9 |
| Rank | 48 | 344 |
| Context | 1M | — |
| Input $/M | $1.25 | — |
| Output $/M | $2.50 | — |
| Weights | Proprietary | Open |

## Coding

- Grok 4.20 (Non-Reasoning): 41.8 (#104)
- Llama 13b: 20.9 (#332)

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 13b |
|---|---|---|
| LMArena Coding | 1458 | 683 |
| LMArena WebDev | 1374 | — |
| WeirdML | 52.3% | — |
| ALE-Bench | 1,150 | — |

## Agentic & Tool Use

- Grok 4.20 (Non-Reasoning): 34.3 (#43)
- Llama 13b: —

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 13b |
|---|---|---|
| Terminal-Bench | 57.3% | — |
| τ²-bench Banking | 18% | — |
| LMArena Search | 1189 | — |
| Vending-Bench 2 | 4,663 | — |

## Reasoning

- Grok 4.20 (Non-Reasoning): 52.2 (#30)
- Llama 13b: 13.4 (#327)

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1451 | 728 |
| Epoch Capabilities Index | 152.01 | 100.09 |
| ARC-AGI-2 | 65.1% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 85.4% | — |
| ARC-AGI-1 | 89.5% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 63.8% | — |
| DTBench | 90.1% | — |
| LMCA | 38.7% | — |
| BIG-Bench Hard | — | 37.9% |
| ForecastBench | 61.4 | — |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |

## Math

- Grok 4.20 (Non-Reasoning): 48.0 (#54)
- Llama 13b: 24.4 (#259)

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 13b |
|---|---|---|
| LMArena Math | 1455 | 838 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| ProofBench | 14% | — |
| GSM8K | — | 20.6% |

## Knowledge

- Grok 4.20 (Non-Reasoning): 52.8 (#54)
- Llama 13b: —

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 13b |
|---|---|---|
| GPQA Diamond | 89.3% | — |
| SimpleQA Verified | 30.2% | — |
| LMArena Expert | 1440 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |

## Multimodal

- Grok 4.20 (Non-Reasoning): 33.2 (#88)
- Llama 13b: —

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 13b |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |
| ScienceQA | — | 43.3% |

## Multilingual

- Grok 4.20 (Non-Reasoning): 54.7 (#38)
- Llama 13b: 16.8 (#292)

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 13b |
|---|---|---|
| LMArena Non-English | 1440 | 819 |
| LMArena Chinese | 1481 | — |
| LMArena French | 1477 | — |
| LMArena German | 1463 | — |
| LMArena Japanese | 1450 | — |
| LMArena Korean | 1417 | — |
| LMArena Russian | 1457 | — |
| LMArena Spanish | 1442 | — |

## Instruction Following

- Grok 4.20 (Non-Reasoning): 75.0 (#79)
- Llama 13b: 36.9 (#300)

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1420 | 781 |

## Long Context

- Grok 4.20 (Non-Reasoning): 45.4 (#33)
- Llama 13b: —

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 13b |
|---|---|---|
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |
| LMArena Longer Query | 1436 | — |

## Writing & Preference

- Grok 4.20 (Non-Reasoning): 65.9 (#42)
- Llama 13b: 13.9 (#307)

| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 13b |
|---|---|---|
| LMArena Text | 1451 | 834 |
| LMArena Creative Writing | 1439 | 794 |
| LMArena Multi-Turn | 1456 | 753 |
| EQ-Bench Creative Writing | 1574 | — |

## FAQ

### Is Grok 4.20 (Non-Reasoning) better than Llama 13b?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 23.9 on the Noometry Index.

### Is Grok 4.20 (Non-Reasoning) or Llama 13b better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 20.9 in the Noometry coding category.

### How many benchmarks do Grok 4.20 (Non-Reasoning) and Llama 13b share?

9 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Llama 13b has 21.