# Grok 4.5 vs Llama 3.2 90B

> Grok 4.5 is the stronger model overall, scoring 55.0 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-4-5-vs-llama-3-2-90b
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Grok 4.5 scores higher in 5 categories and Llama 3.2 90B in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.5 leads 60.7 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 97.8% for Grok 4.5 and 2.6% for Llama 3.2 90B.
- Llama 3.2 90B has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.5 | Llama 3.2 90B |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 55.0 | 27.1 |
| Rank | 22 | 326 |
| Context | 500K | — |
| Input $/M | $2 | — |
| Output $/M | $6 | — |
| Weights | Proprietary | Open |

## Coding

- Grok 4.5: 51.7 (#34)
- Llama 3.2 90B: —

| Benchmark | Grok 4.5 | Llama 3.2 90B |
|---|---|---|
| DeepSWE | 53.8% | — |
| FrontierCode | 42.4% | — |
| LMArena WebDev | 1552 | — |
| SciCode | 54.1% | — |
| WeirdML | 46.4% | — |
| LMArena Coding | 1473 | — |
| ALE-Bench | 1,309 | — |

## Agentic & Tool Use

- Grok 4.5: 44.4 (#15)
- Llama 3.2 90B: 29.7 (#73)

| Benchmark | Grok 4.5 | Llama 3.2 90B |
|---|---|---|
| APEX-Agents | 56.2% | — |
| τ²-bench Banking | 47.9% | — |
| PostTrainBench | 23.4% | — |
| BALROG | — | 27.3% |
| GBAEval | 65.4% | — |
| GDP.pdf | 14% | — |
| LMArena Search | 1213 | — |
| Vending-Bench 2 | 3,887 | — |

## Reasoning

- Grok 4.5: 56.0 (#23)
- Llama 3.2 90B: 20.9 (#207)

| Benchmark | Grok 4.5 | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 154.02 | 125.5 |
| ARC-AGI-2 | 52.6% | — |
| SimpleBench | 70% | — |
| Kagi LLM Benchmark | 83.5% | — |
| NYT Connections (extended) | 79.9% | — |
| ARC-AGI-1 | 87.2% | — |
| CritPt | 15.4% | — |
| Chess Puzzles | 36% | — |
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1462 | — |
| DTBench | 96.5% | — |
| LMCA | 45.2% | — |
| Surface Evolver Bench | 74.4% | — |

## Math

- Grok 4.5: 60.7 (#29)
- Llama 3.2 90B: 10.4 (#302)

| Benchmark | Grok 4.5 | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 97.8% | 2.6% |
| FrontierMath (Tiers 1-3) | 57.2% | — |
| FrontierMath Tier 4 | 24.4% | — |
| ProofBench | 31% | — |
| LMArena Math | 1457 | — |
| MATH Level 5 | — | 39.4% |

## Knowledge

- Grok 4.5: 62.3 (#21)
- Llama 3.2 90B: 21.7 (#269)

| Benchmark | Grok 4.5 | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 93.4% | 41% |
| SimpleQA Verified | 48.3% | — |
| LMArena Expert | 1466 | — |
| MMLU | — | 80.3% |

## Multimodal

- Grok 4.5: 37.8 (#63)
- Llama 3.2 90B: 24.9 (#119)

| Benchmark | Grok 4.5 | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | 1287 | 1000 |
| GeoBench | — | 52% |
| Blueprint-Bench 2 | 27.3% | — |
| Furniture Assembly | 22.5% | — |
| LMArena Document | 1452 | — |

## Multilingual

- Grok 4.5: 54.5 (#43)
- Llama 3.2 90B: —

| Benchmark | Grok 4.5 | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1439 | — |
| LMArena Chinese | 1497 | — |
| LMArena French | 1458 | — |
| LMArena German | 1448 | — |
| LMArena Japanese | 1425 | — |
| LMArena Korean | 1402 | — |
| LMArena Russian | 1447 | — |
| LMArena Spanish | 1452 | — |

## Instruction Following

- Grok 4.5: 76.3 (#45)
- Llama 3.2 90B: —

| Benchmark | Grok 4.5 | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1446 | — |

## Long Context

- Grok 4.5: 44.8 (#54)
- Llama 3.2 90B: —

| Benchmark | Grok 4.5 | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1463 | — |

## Writing & Preference

- Grok 4.5: 65.9 (#40)
- Llama 3.2 90B: —

| Benchmark | Grok 4.5 | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1448 | — |
| LMArena Creative Writing | 1442 | — |
| EQ-Bench Creative Writing | 1579 | — |
| LMArena Multi-Turn | 1457 | — |

## FAQ

### Is Grok 4.5 better than Llama 3.2 90B?

Grok 4.5 is the stronger model overall, scoring 55.0 to 27.1 on the Noometry Index.

### How many benchmarks do Grok 4.5 and Llama 3.2 90B share?

4 benchmarks have published results for both models. Grok 4.5 has 52 scored results on Noometry and Llama 3.2 90B has 9.