Model comparison
Grok 4.1 vs Llama 3.2 90B
Grok 4.1 is the stronger model overall, scoring 41.5 to 27.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
MetaSummary
- The widest gap is in math, where Grok 4.1 leads 38.9 to 11.1.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| Grok 4.1 | Llama 3.2 90B | |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 41.5 | 27.5 |
| Released | 2025-11-17 | 2024-09-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Grok 4.1: 33.7 (#253), Llama 3.2 90B: —
| Benchmark | Grok 4.1 | Llama 3.2 90B |
|---|---|---|
| LMArena WebDev | 1214 | — |
| LMArena Coding | 1445 | — |
Agentic & Tool Use Grok 4.1 leads
Grok 4.1: 34.1 (#49), Llama 3.2 90B: 30.0 (#80)
Reasoning Grok 4.1 leads
Grok 4.1: 29.5 (#91), Llama 3.2 90B: 21.7 (#217)
| Benchmark | Grok 4.1 | Llama 3.2 90B |
|---|---|---|
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1435 | — |
| Epoch Capabilities Index | — | 125.5 |
Math Grok 4.1 leads
Grok 4.1: 38.9 (#120), Llama 3.2 90B: 11.1 (#308)
| Benchmark | Grok 4.1 | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| LMArena Math | 1422 | — |
| MATH Level 5 | — | 39.4% |
Knowledge Grok 4.1 leads
Grok 4.1: 39.5 (#133), Llama 3.2 90B: 21.7 (#274)
| Benchmark | Grok 4.1 | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | — | 41% |
| LMArena Expert | 1417 | — |
| MMLU | — | 80.3% |
Multimodal Not comparable
Grok 4.1: —, Llama 3.2 90B: 25.4 (#124)
| Benchmark | Grok 4.1 | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
Multilingual Not comparable
Grok 4.1: 53.4 (#68), Llama 3.2 90B: —
| Benchmark | Grok 4.1 | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1425 | — |
| LMArena Chinese | 1465 | — |
| LMArena French | 1448 | — |
| LMArena German | 1446 | — |
| LMArena Japanese | 1397 | — |
| LMArena Korean | 1407 | — |
| LMArena Russian | 1434 | — |
| LMArena Spanish | 1438 | — |
Instruction Following Not comparable
Grok 4.1: 73.8 (#111), Llama 3.2 90B: —
| Benchmark | Grok 4.1 | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1400 | — |
Long Context Not comparable
Grok 4.1: 43.2 (#100), Llama 3.2 90B: —
| Benchmark | Grok 4.1 | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1416 | — |
Writing & Preference Not comparable
Grok 4.1: 62.4 (#75), Llama 3.2 90B: —
| Benchmark | Grok 4.1 | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1437 | — |
| LMArena Creative Writing | 1411 | — |
| LMArena Multi-Turn | 1437 | — |
Frequently asked questions
Is Grok 4.1 better than Llama 3.2 90B?
Grok 4.1 is the stronger model overall, scoring 41.5 to 27.5 on the Noometry Index.
How many benchmarks do Grok 4.1 and Llama 3.2 90B share?
0 benchmarks have published results for both models. Grok 4.1 has 19 scored results on Noometry and Llama 3.2 90B has 9.