# Grok 4.3 vs Llama 3.1-405B

> Grok 4.3 is the stronger model overall, scoring 43.8 to 30.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-4-3-vs-llama-3-1-405b
- Last updated: 2026-10-12
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Grok 4.3 scores higher in 9 categories and Llama 3.1-405B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.3 leads 46.0 to 18.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for Grok 4.3 and 9.7% for Llama 3.1-405B.
- Llama 3.1-405B has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.3 | Llama 3.1-405B |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 43.8 | 30.7 |
| Rank | 86 | 288 |
| Context | 1M | — |
| Input $/M | $1.25 | — |
| Output $/M | $2.50 | — |
| Weights | Proprietary | Open |

## Coding

- Grok 4.3: 41.6 (#121)
- Llama 3.1-405B: 33.1 (#262)

| Benchmark | Grok 4.3 | Llama 3.1-405B |
|---|---|---|
| WeirdML | 49.9% | 21.4% |
| LMArena Coding | 1415 | 1291 |
| LMArena WebDev | 1357 | — |
| SciCode | 47.3% | — |
| ALE-Bench | 944.17 | — |

## Agentic & Tool Use

- Grok 4.3: 27.7 (#99)
- Llama 3.1-405B: 21.0 (#140)

| Benchmark | Grok 4.3 | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
| GDP.pdf | 8% | — |
| LMArena Search | 1165 | — |
| Vending-Bench 2 | 35.26 | — |

## Reasoning

- Grok 4.3: 35.9 (#68)
- Llama 3.1-405B: 16.8 (#300)

| Benchmark | Grok 4.3 | Llama 3.1-405B |
|---|---|---|
| LMArena Hard Prompts | 1396 | 1269 |
| DTBench | 90.7% | 61.4% |
| Epoch Capabilities Index | 149.16 | 128.75 |
| ForecastBench | 60.3 | 59.9 |
| SimpleBench | — | 23% |
| Kagi LLM Benchmark | — | 45% |
| NYT Connections (extended) | 55.2% | — |
| CritPt | 8% | — |
| Chess Puzzles | 25% | — |
| LMCA | 38.3% | — |
| BIG-Bench Hard | — | 82.9% |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |

## Math

- Grok 4.3: 46.0 (#74)
- Llama 3.1-405B: 18.4 (#290)

| Benchmark | Grok 4.3 | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 9.7% |
| LMArena Math | 1388 | 1281 |
| FrontierMath (Tiers 1-3) | 42.8% | — |
| FrontierMath Tier 4 | 14.6% | — |
| ProofBench | 11% | — |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |

## Knowledge

- Grok 4.3: 52.5 (#62)
- Llama 3.1-405B: 30.4 (#227)

| Benchmark | Grok 4.3 | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 88.8% | 50.9% |
| LMArena Expert | 1385 | 1243 |
| SimpleQA Verified | 33.2% | — |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |

## Multimodal

- Grok 4.3: 31.6 (#104)
- Llama 3.1-405B: —

| Benchmark | Grok 4.3 | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1229 | — |
| Blueprint-Bench 2 | 0% | — |

## Multilingual

- Grok 4.3: 50.5 (#120)
- Llama 3.1-405B: 40.7 (#214)

| Benchmark | Grok 4.3 | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1385 | 1248 |
| LMArena Chinese | 1422 | 1242 |
| LMArena French | 1412 | 1279 |
| LMArena German | 1395 | 1252 |
| LMArena Japanese | 1379 | 1208 |
| LMArena Korean | 1356 | 1184 |
| LMArena Russian | 1399 | 1265 |
| LMArena Spanish | 1398 | 1260 |

## Instruction Following

- Grok 4.3: 72.1 (#140)
- Llama 3.1-405B: 65.9 (#214)

| Benchmark | Grok 4.3 | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1366 | 1259 |
| IFEval | — | 81.1% |

## Long Context

- Grok 4.3: 42.5 (#123)
- Llama 3.1-405B: 38.4 (#197)

| Benchmark | Grok 4.3 | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1393 | 1266 |

## Writing & Preference

- Grok 4.3: 58.5 (#118)
- Llama 3.1-405B: 38.9 (#251)

| Benchmark | Grok 4.3 | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1397 | 1284 |
| LMArena Creative Writing | 1380 | 1262 |
| LMArena Multi-Turn | 1406 | 1297 |
| EQ-Bench Creative Writing | — | 870 |
| WildBench | — | 78.3% |
| EQ-Bench 4 | 1075 | — |

## FAQ

### Is Grok 4.3 better than Llama 3.1-405B?

Grok 4.3 is the stronger model overall, scoring 43.8 to 30.7 on the Noometry Index.

### Is Grok 4.3 or Llama 3.1-405B better for coding?

Grok 4.3 scores higher on coding benchmarks: 41.6 versus 33.1 in the Noometry coding category.

### How many benchmarks do Grok 4.3 and Llama 3.1-405B share?

23 benchmarks have published results for both models. Grok 4.3 has 40 scored results on Noometry and Llama 3.1-405B has 42.