# Grok 4.3 vs Llama 2-13B

> Grok 4.3 is the stronger model overall, scoring 43.8 to 29.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-4-3-vs-llama-2-13b
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Grok 4.3 scores higher in 8 categories and Llama 2-13B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 4.3 leads 58.5 to 29.8.
- The biggest single-benchmark swing is DTBench: 90.7% for Grok 4.3 and 42.2% for Llama 2-13B.
- Llama 2-13B has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.3 | Llama 2-13B |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 43.8 | 29.6 |
| Rank | 86 | 309 |
| Context | 1M | — |
| Input $/M | $1.25 | — |
| Output $/M | $2.50 | — |
| Weights | Proprietary | Open |

## Coding

- Grok 4.3: 41.6 (#121)
- Llama 2-13B: 30.9 (#291)

| Benchmark | Grok 4.3 | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1415 | 1062 |
| LMArena WebDev | 1357 | — |
| SciCode | 47.3% | — |
| WeirdML | 49.9% | — |
| ALE-Bench | 944.17 | — |

## Agentic & Tool Use

- Grok 4.3: 27.7 (#99)
- Llama 2-13B: —

| Benchmark | Grok 4.3 | Llama 2-13B |
|---|---|---|
| GDP.pdf | 8% | — |
| LMArena Search | 1165 | — |
| Vending-Bench 2 | 35.26 | — |

## Reasoning

- Grok 4.3: 35.9 (#68)
- Llama 2-13B: 12.8 (#337)

| Benchmark | Grok 4.3 | Llama 2-13B |
|---|---|---|
| Chess Puzzles | 25% | 0% |
| LMArena Hard Prompts | 1396 | 1051 |
| DTBench | 90.7% | 42.2% |
| Epoch Capabilities Index | 149.16 | 106.17 |
| NYT Connections (extended) | 55.2% | — |
| CritPt | 8% | — |
| LMCA | 38.3% | — |
| BIG-Bench Hard | — | 58.2% |
| ForecastBench | 60.3 | — |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |

## Math

- Grok 4.3: 46.0 (#74)
- Llama 2-13B: 31.1 (#229)

| Benchmark | Grok 4.3 | Llama 2-13B |
|---|---|---|
| LMArena Math | 1388 | 1065 |
| FrontierMath (Tiers 1-3) | 42.8% | — |
| FrontierMath Tier 4 | 14.6% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 11% | — |
| GSM8K | — | 36.9% |

## Knowledge

- Grok 4.3: 52.5 (#62)
- Llama 2-13B: 28.1 (#249)

| Benchmark | Grok 4.3 | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1385 | 1030 |
| GPQA Diamond | 88.8% | — |
| SimpleQA Verified | 33.2% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |

## Multimodal

- Grok 4.3: 31.6 (#104)
- Llama 2-13B: —

| Benchmark | Grok 4.3 | Llama 2-13B |
|---|---|---|
| LMArena Vision | 1229 | — |
| Blueprint-Bench 2 | 0% | — |
| ScienceQA | — | 55.8% |

## Multilingual

- Grok 4.3: 50.5 (#120)
- Llama 2-13B: 26.5 (#279)

| Benchmark | Grok 4.3 | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1385 | 1024 |
| LMArena Chinese | 1422 | 1001 |
| LMArena French | 1412 | 1044 |
| LMArena German | 1395 | 1009 |
| LMArena Japanese | 1379 | 894 |
| LMArena Korean | 1356 | 953 |
| LMArena Russian | 1399 | 1055 |
| LMArena Spanish | 1398 | 1087 |

## Instruction Following

- Grok 4.3: 72.1 (#140)
- Llama 2-13B: 53.3 (#287)

| Benchmark | Grok 4.3 | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1366 | 1045 |

## Long Context

- Grok 4.3: 42.5 (#123)
- Llama 2-13B: 32.3 (#269)

| Benchmark | Grok 4.3 | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1393 | 1064 |

## Writing & Preference

- Grok 4.3: 58.5 (#118)
- Llama 2-13B: 29.8 (#289)

| Benchmark | Grok 4.3 | Llama 2-13B |
|---|---|---|
| LMArena Text | 1397 | 1084 |
| LMArena Creative Writing | 1380 | 1047 |
| LMArena Multi-Turn | 1406 | 1050 |
| EQ-Bench 4 | 1075 | — |

## FAQ

### Is Grok 4.3 better than Llama 2-13B?

Grok 4.3 is the stronger model overall, scoring 43.8 to 29.6 on the Noometry Index.

### Is Grok 4.3 or Llama 2-13B better for coding?

Grok 4.3 scores higher on coding benchmarks: 41.6 versus 30.9 in the Noometry coding category.

### How many benchmarks do Grok 4.3 and Llama 2-13B share?

20 benchmarks have published results for both models. Grok 4.3 has 40 scored results on Noometry and Llama 2-13B has 32.