# Grok 4.3 vs Llama 3.2 90B

> Grok 4.3 is the stronger model overall, scoring 43.6 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-4-3-vs-llama-3-2-90b
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Grok 4.3 scores higher in 4 categories and Llama 3.2 90B in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.3 leads 45.8 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for Grok 4.3 and 2.6% for Llama 3.2 90B.
- Llama 3.2 90B has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.3 | Llama 3.2 90B |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 43.6 | 27.1 |
| Rank | 80 | 326 |
| Context | 1M | — |
| Input $/M | $1.25 | — |
| Output $/M | $2.50 | — |
| Weights | Proprietary | Open |

## Coding

- Grok 4.3: 41.3 (#117)
- Llama 3.2 90B: —

| Benchmark | Grok 4.3 | Llama 3.2 90B |
|---|---|---|
| LMArena WebDev | 1357 | — |
| SciCode | 47.3% | — |
| WeirdML | 49.9% | — |
| LMArena Coding | 1415 | — |
| ALE-Bench | 944.17 | — |

## Agentic & Tool Use

- Grok 4.3: 27.6 (#93)
- Llama 3.2 90B: 29.7 (#73)

| Benchmark | Grok 4.3 | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |
| GDP.pdf | 8% | — |
| LMArena Search | 1165 | — |
| Vending-Bench 2 | 35.26 | — |

## Reasoning

- Grok 4.3: 34.9 (#60)
- Llama 3.2 90B: 20.9 (#207)

| Benchmark | Grok 4.3 | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 149.13 | 125.5 |
| NYT Connections (extended) | 55.2% | — |
| CritPt | 8% | — |
| Chess Puzzles | 25% | — |
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1397 | — |
| DTBench | 90.7% | — |
| LMCA | 38.3% | — |
| ForecastBench | 60.3 | — |

## Math

- Grok 4.3: 45.8 (#60)
- Llama 3.2 90B: 10.4 (#302)

| Benchmark | Grok 4.3 | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 2.6% |
| FrontierMath (Tiers 1-3) | 42.8% | — |
| FrontierMath Tier 4 | 14.6% | — |
| ProofBench | 11% | — |
| LMArena Math | 1388 | — |
| MATH Level 5 | — | 39.4% |

## Knowledge

- Grok 4.3: 52.5 (#57)
- Llama 3.2 90B: 21.7 (#269)

| Benchmark | Grok 4.3 | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 88.8% | 41% |
| SimpleQA Verified | 33.2% | — |
| LMArena Expert | 1385 | — |
| MMLU | — | 80.3% |

## Multimodal

- Grok 4.3: 31.6 (#96)
- Llama 3.2 90B: 24.9 (#119)

| Benchmark | Grok 4.3 | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | 1231 | 1000 |
| GeoBench | — | 52% |
| Blueprint-Bench 2 | 0% | — |

## Multilingual

- Grok 4.3: 50.7 (#114)
- Llama 3.2 90B: —

| Benchmark | Grok 4.3 | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1385 | — |
| LMArena Chinese | 1423 | — |
| LMArena French | 1412 | — |
| LMArena German | 1395 | — |
| LMArena Japanese | 1379 | — |
| LMArena Korean | 1357 | — |
| LMArena Russian | 1399 | — |
| LMArena Spanish | 1402 | — |

## Instruction Following

- Grok 4.3: 72.3 (#135)
- Llama 3.2 90B: —

| Benchmark | Grok 4.3 | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1366 | — |

## Long Context

- Grok 4.3: 42.5 (#118)
- Llama 3.2 90B: —

| Benchmark | Grok 4.3 | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1393 | — |

## Writing & Preference

- Grok 4.3: 58.6 (#112)
- Llama 3.2 90B: —

| Benchmark | Grok 4.3 | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1397 | — |
| LMArena Creative Writing | 1380 | — |
| EQ-Bench 4 | 1075 | — |
| LMArena Multi-Turn | 1406 | — |

## FAQ

### Is Grok 4.3 better than Llama 3.2 90B?

Grok 4.3 is the stronger model overall, scoring 43.6 to 27.1 on the Noometry Index.

### How many benchmarks do Grok 4.3 and Llama 3.2 90B share?

4 benchmarks have published results for both models. Grok 4.3 has 40 scored results on Noometry and Llama 3.2 90B has 9.