# Grok-3 mini vs Llama 3.2 90B

> Grok-3 mini is the stronger model overall, scoring 41.0 to 27.1 on the Noometry Index.

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

## Summary

- They share 4 benchmarks with published results for both. Grok-3 mini scores higher in 2 categories and Llama 3.2 90B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok-3 mini leads 40.3 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 2.6% for Llama 3.2 90B.
- Llama 3.2 90B has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-3 mini | Llama 3.2 90B |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 41.0 | 27.1 |
| Rank | 130 | 326 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Grok-3 mini: 40.4 (#126)
- Llama 3.2 90B: —

| Benchmark | Grok-3 mini | Llama 3.2 90B |
|---|---|---|
| Aider Polyglot | 49.3% | — |
| WeirdML | 42.6% | — |
| LMArena Coding | 1380 | — |

## Agentic & Tool Use

- Grok-3 mini: —
- Llama 3.2 90B: 29.7 (#73)

| Benchmark | Grok-3 mini | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |

## Reasoning

- Grok-3 mini: 13.8 (#323)
- Llama 3.2 90B: 20.9 (#207)

| Benchmark | Grok-3 mini | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 140.35 | 125.5 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1374 | — |

## Math

- Grok-3 mini: 40.3 (#78)
- Llama 3.2 90B: 10.4 (#302)

| Benchmark | Grok-3 mini | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 2.6% |
| MATH Level 5 | 90.9% | 39.4% |
| Omni-MATH | 31.8% | — |
| LMArena Math | 1386 | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |

## Knowledge

- Grok-3 mini: 46.3 (#75)
- Llama 3.2 90B: 21.7 (#269)

| Benchmark | Grok-3 mini | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 76.3% | 41% |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
| LMArena Expert | 1395 | — |
| MMLU | — | 80.3% |

## Multimodal

- Grok-3 mini: —
- Llama 3.2 90B: 24.9 (#119)

| Benchmark | Grok-3 mini | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |

## Multilingual

- Grok-3 mini: 48.3 (#141)
- Llama 3.2 90B: —

| Benchmark | Grok-3 mini | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1352 | — |
| LMArena Chinese | 1387 | — |
| LMArena French | 1357 | — |
| LMArena German | 1350 | — |
| LMArena Japanese | 1343 | — |
| LMArena Korean | 1336 | — |
| LMArena Russian | 1352 | — |
| LMArena Spanish | 1379 | — |

## Instruction Following

- Grok-3 mini: 78.7 (#8)
- Llama 3.2 90B: —

| Benchmark | Grok-3 mini | Llama 3.2 90B |
|---|---|---|
| IFEval | 95.1% | — |
| LMArena Instruction Following | 1356 | — |

## Long Context

- Grok-3 mini: 41.0 (#142)
- Llama 3.2 90B: —

| Benchmark | Grok-3 mini | Llama 3.2 90B |
|---|---|---|
| Fiction.LiveBench | 66.7% | — |
| LMArena Longer Query | 1372 | — |

## Writing & Preference

- Grok-3 mini: 52.7 (#163)
- Llama 3.2 90B: —

| Benchmark | Grok-3 mini | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1370 | — |
| LMArena Creative Writing | 1342 | — |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
| LMArena Multi-Turn | 1355 | — |

## FAQ

### Is Grok-3 mini better than Llama 3.2 90B?

Grok-3 mini is the stronger model overall, scoring 41.0 to 27.1 on the Noometry Index.

### How many benchmarks do Grok-3 mini and Llama 3.2 90B share?

4 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Llama 3.2 90B has 9.