Model comparison
Grok 3 vs Llama 3.2 90B
Grok 3 is the stronger model overall, scoring 39.9 to 27.5 on the Noometry Index.
Last verified . 5 shared benchmarks.
MetaSummary
- They share 5 benchmarks with published results for both. Grok 3 scores higher in 3 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 leads 38.0 to 11.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 55.6% for Grok 3 and 2.6% for Llama 3.2 90B.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| Grok 3 | Llama 3.2 90B | |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 39.9 | 27.5 |
| Released | 2025-04-09 | 2024-09-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 40 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Grok 3: 41.9 (#115), Llama 3.2 90B: —
| Benchmark | Grok 3 | Llama 3.2 90B |
|---|---|---|
| Aider Polyglot | 53.3% | — |
| WeirdML | 37.2% | — |
| LMArena Coding | 1432 | — |
Agentic & Tool Use Too close to call
Grok 3: 30.5 (#76), Llama 3.2 90B: 30.0 (#80)
| Benchmark | Grok 3 | Llama 3.2 90B |
|---|---|---|
| BALROG | 29.5% | 27.3% |
Reasoning Llama 3.2 90B leads
Grok 3: 13.7 (#333), Llama 3.2 90B: 21.7 (#217)
| Benchmark | Grok 3 | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 138.33 | 125.5 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1434 | — |
Math Grok 3 leads
Grok 3: 38.0 (#145), Llama 3.2 90B: 11.1 (#308)
| Benchmark | Grok 3 | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6% | 2.6% |
| MATH Level 5 | 88.7% | 39.4% |
| Omni-MATH | 46.4% | — |
| LMArena Math | 1391 | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 3 leads
Grok 3: 46.2 (#82), Llama 3.2 90B: 21.7 (#274)
| Benchmark | Grok 3 | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 75.8% | 41% |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |
| LMArena Expert | 1421 | — |
| MMLU | — | 80.3% |
Multimodal Not comparable
Grok 3: —, Llama 3.2 90B: 25.4 (#124)
| Benchmark | Grok 3 | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
Multilingual Not comparable
Grok 3: 52.3 (#87), Llama 3.2 90B: —
| Benchmark | Grok 3 | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1410 | — |
| LMArena Chinese | 1448 | — |
| LMArena French | 1460 | — |
| LMArena German | 1431 | — |
| LMArena Japanese | 1387 | — |
| LMArena Korean | 1373 | — |
| LMArena Russian | 1416 | — |
| LMArena Spanish | 1417 | — |
Instruction Following Not comparable
Grok 3: 75.0 (#73), Llama 3.2 90B: —
| Benchmark | Grok 3 | Llama 3.2 90B |
|---|---|---|
| IFEval | 88.4% | — |
| LMArena Instruction Following | 1409 | — |
Long Context Not comparable
Grok 3: 38.7 (#192), Llama 3.2 90B: —
| Benchmark | Grok 3 | Llama 3.2 90B |
|---|---|---|
| Fiction.LiveBench | 58.3% | — |
| LMArena Longer Query | 1439 | — |
Writing & Preference Not comparable
Grok 3: 55.8 (#141), Llama 3.2 90B: —
| Benchmark | Grok 3 | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1426 | — |
| LMArena Creative Writing | 1414 | — |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
| LMArena Multi-Turn | 1425 | — |
Frequently asked questions
Is Grok 3 better than Llama 3.2 90B?
Grok 3 is the stronger model overall, scoring 39.9 to 27.5 on the Noometry Index.
How many benchmarks do Grok 3 and Llama 3.2 90B share?
5 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Llama 3.2 90B has 9.