Model comparison
Grok 4.20 (Non-Reasoning) vs Llama 3.1-405B
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 30.7 on the Noometry Index.
Last verified . 25 shared benchmarks.
MetaSummary
- They share 25 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 9 categories and Llama 3.1-405B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 16.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 92.2% for Grok 4.20 (Non-Reasoning) and 9.7% for Llama 3.1-405B.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Grok 4.20 (Non-Reasoning) | Llama 3.1-405B | |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 48.6 | 30.7 |
| Released | 2026-02-17 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 30K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 46 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 42.1 (#112), Llama 3.1-405B: 33.1 (#262)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.1-405B |
|---|---|---|
| WeirdML | 52.3% | 21.4% |
| LMArena Coding | 1459 | 1291 |
| LMArena WebDev | 1375 | — |
| ALE-Bench | 1,150 | — |
Agentic & Tool Use Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 34.4 (#46), Llama 3.1-405B: 21.0 (#140)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.1-405B |
|---|---|---|
| Terminal-Bench | 57.3% | — |
| TheAgentCompany | — | 7.4% |
| τ²-bench Banking | 18% | — |
| Cybench | — | 7.5% |
| LMArena Search | 1189 | — |
| Vending-Bench 2 | 4,663 | — |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.3 (#32), Llama 3.1-405B: 16.8 (#300)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.1-405B |
|---|---|---|
| Kagi LLM Benchmark | 75% | 45% |
| LMArena Hard Prompts | 1451 | 1269 |
| DTBench | 90.1% | 61.4% |
| Epoch Capabilities Index | 151.98 | 128.75 |
| ForecastBench | 61.4 | 59.9 |
| ARC-AGI-2 | 65.1% | — |
| SimpleBench | — | 23% |
| NYT Connections (extended) | 85.4% | — |
| ARC-AGI-1 | 89.5% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 63.8% | — |
| LMCA | 38.7% | — |
| BIG-Bench Hard | — | 82.9% |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 48.2 (#65), Llama 3.1-405B: 18.4 (#290)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 92.2% | 9.7% |
| LMArena Math | 1455 | 1281 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 14% | — |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |
Knowledge Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.8 (#60), Llama 3.1-405B: 30.4 (#227)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 89.3% | 50.9% |
| LMArena Expert | 1439 | 1243 |
| SimpleQA Verified | 30.2% | — |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |
Multimodal Not comparable
Grok 4.20 (Non-Reasoning): 33.3 (#98), Llama 3.1-405B: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |
Multilingual Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 54.5 (#40), Llama 3.1-405B: 40.7 (#214)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1441 | 1248 |
| LMArena Chinese | 1481 | 1242 |
| LMArena French | 1476 | 1279 |
| LMArena German | 1465 | 1252 |
| LMArena Japanese | 1449 | 1208 |
| LMArena Korean | 1417 | 1184 |
| LMArena Russian | 1458 | 1265 |
| LMArena Spanish | 1443 | 1260 |
Instruction Following Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 74.8 (#83), Llama 3.1-405B: 65.9 (#214)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1420 | 1259 |
| IFEval | — | 81.1% |
Long Context Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 45.5 (#34), Llama 3.1-405B: 38.4 (#197)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1437 | 1266 |
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 65.7 (#44), Llama 3.1-405B: 38.9 (#251)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1451 | 1284 |
| LMArena Creative Writing | 1438 | 1262 |
| EQ-Bench Creative Writing | 1574 | 870 |
| LMArena Multi-Turn | 1456 | 1297 |
| WildBench | — | 78.3% |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Llama 3.1-405B?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 30.7 on the Noometry Index.
Is Grok 4.20 (Non-Reasoning) or Llama 3.1-405B better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 33.1 in the Noometry coding category.
How many benchmarks do Grok 4.20 (Non-Reasoning) and Llama 3.1-405B share?
25 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Llama 3.1-405B has 42.