Model comparison
Grok 4 Fast vs Llama 3.2 90B
Grok 4 Fast is the stronger model overall, scoring 39.4 to 27.5 on the Noometry Index.
Last verified . 1 shared benchmarks.
MetaSummary
- They share 1 benchmark with published results for both. Grok 4 Fast scores higher in 3 categories and Llama 3.2 90B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4 Fast leads 38.9 to 11.1.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| Grok 4 Fast | Llama 3.2 90B | |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 39.4 | 27.5 |
| Released | 2025-09-19 | 2024-09-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 30 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Grok 4 Fast: 32.5 (#271), Llama 3.2 90B: —
| Benchmark | Grok 4 Fast | Llama 3.2 90B |
|---|---|---|
| LMArena WebDev | 1159 | — |
| WeirdML | 42.9% | — |
| LMArena Coding | 1429 | — |
Agentic & Tool Use Too close to call
Grok 4 Fast: 29.5 (#86), Llama 3.2 90B: 30.0 (#80)
| Benchmark | Grok 4 Fast | Llama 3.2 90B |
|---|---|---|
| τ²-bench Banking | 15.7% | — |
| Cybench | 30% | — |
| BALROG | — | 27.3% |
| LMArena Search | 1171 | — |
Reasoning Too close to call
Grok 4 Fast: 22.2 (#201), Llama 3.2 90B: 21.7 (#217)
| Benchmark | Grok 4 Fast | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 144.2 | 125.5 |
| ARC-AGI-2 | 5.3% | — |
| Kagi LLM Benchmark | 66.1% | — |
| ARC-AGI-1 | 48.5% | — |
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1412 | — |
| DTBench | 82.7% | — |
| ForecastBench | 60.5 | — |
Math Grok 4 Fast leads
Grok 4 Fast: 38.9 (#123), Llama 3.2 90B: 11.1 (#308)
| Benchmark | Grok 4 Fast | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| LMArena Math | 1419 | — |
| MATH Level 5 | — | 39.4% |
Knowledge Grok 4 Fast leads
Grok 4 Fast: 32.0 (#214), Llama 3.2 90B: 21.7 (#274)
| Benchmark | Grok 4 Fast | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | — | 41% |
| Vectara Hallucination Rate | 19.7% | — |
| LMArena Expert | 1411 | — |
| MMLU | — | 80.3% |
Multimodal Not comparable
Grok 4 Fast: —, Llama 3.2 90B: 25.4 (#124)
| Benchmark | Grok 4 Fast | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
Multilingual Not comparable
Grok 4 Fast: 51.3 (#111), Llama 3.2 90B: —
| Benchmark | Grok 4 Fast | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1396 | — |
| LMArena Chinese | 1457 | — |
| LMArena French | 1431 | — |
| LMArena German | 1383 | — |
| LMArena Japanese | 1352 | — |
| LMArena Korean | 1357 | — |
| LMArena Russian | 1389 | — |
| LMArena Spanish | 1415 | — |
Instruction Following Not comparable
Grok 4 Fast: 73.2 (#121), Llama 3.2 90B: —
| Benchmark | Grok 4 Fast | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1387 | — |
Long Context Not comparable
Grok 4 Fast: 63.2 (#3), Llama 3.2 90B: —
| Benchmark | Grok 4 Fast | Llama 3.2 90B |
|---|---|---|
| Fiction.LiveBench | 94.4% | — |
| LMArena Longer Query | 1415 | — |
Writing & Preference Not comparable
Grok 4 Fast: 60.0 (#102), Llama 3.2 90B: —
| Benchmark | Grok 4 Fast | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1407 | — |
| LMArena Creative Writing | 1387 | — |
| LMArena Multi-Turn | 1414 | — |
Frequently asked questions
Is Grok 4 Fast better than Llama 3.2 90B?
Grok 4 Fast is the stronger model overall, scoring 39.4 to 27.5 on the Noometry Index.
How many benchmarks do Grok 4 Fast and Llama 3.2 90B share?
1 benchmark has published results for both models. Grok 4 Fast has 30 scored results on Noometry and Llama 3.2 90B has 9.