Model comparison
Grok 4.6 vs Llama 3.1-405B
Grok 4.6 is the stronger model overall, scoring 56.9 to 30.7 on the Noometry Index.
Last verified . 23 shared benchmarks.
MetaSummary
- They share 23 benchmarks with published results for both. Grok 4.6 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 math, where Grok 4.6 leads 67.0 to 18.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 99.2% for Grok 4.6 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 4.6 | Llama 3.1-405B | |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 56.9 | 30.7 |
| Released | 2026-08-12 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | 500K | — |
| Max output | 500K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 49 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
Grok 4.6: 58.5 (#16), Llama 3.1-405B: 33.1 (#262)
| Benchmark | Grok 4.6 | Llama 3.1-405B |
|---|---|---|
| WeirdML | 67.3% | 21.4% |
| LMArena Coding | 1465 | 1291 |
| DeepSWE | 67.5% | — |
| FrontierCode | 48% | — |
| CursorBench | 41.4% | — |
| LMArena WebDev | 1617 | — |
| FrontierSWE | 25.3% | — |
| SciCode | 56.5% | — |
| ALE-Bench | 1,508 | — |
Agentic & Tool Use Grok 4.6 leads
Grok 4.6: 39.4 (#27), Llama 3.1-405B: 21.0 (#140)
| Benchmark | Grok 4.6 | Llama 3.1-405B |
|---|---|---|
| APEX-Agents | 65.3% | — |
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
| GDP.pdf | 17.2% | — |
| Vending-Bench 2 | 9,047 | — |
Reasoning Grok 4.6 leads
Grok 4.6: 61.4 (#20), Llama 3.1-405B: 16.8 (#300)
| Benchmark | Grok 4.6 | Llama 3.1-405B |
|---|---|---|
| SimpleBench | 75.9% | 23% |
| LMArena Hard Prompts | 1447 | 1269 |
| DTBench | 97.3% | 61.4% |
| Epoch Capabilities Index | 156.44 | 128.75 |
| ARC-AGI-2 | 67.1% | — |
| Kagi LLM Benchmark | — | 45% |
| NYT Connections (extended) | 80% | — |
| ARC-AGI-1 | 87.5% | — |
| CritPt | 19.7% | — |
| Chess Puzzles | 40% | — |
| EBR-Bench | 30.5% | — |
| Mystery Game Puzzles | 34% | — |
| LMCA | 48.5% | — |
| BIG-Bench Hard | — | 82.9% |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math Grok 4.6 leads
Grok 4.6: 67.0 (#24), Llama 3.1-405B: 18.4 (#290)
| Benchmark | Grok 4.6 | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 99.2% | 9.7% |
| LMArena Math | 1423 | 1281 |
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 31.7% | — |
| ProofBench | 51% | — |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |
Knowledge Grok 4.6 leads
Grok 4.6: 63.3 (#20), Llama 3.1-405B: 30.4 (#227)
| Benchmark | Grok 4.6 | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 94% | 50.9% |
| LMArena Expert | 1467 | 1243 |
| SimpleQA Verified | 49.3% | — |
| 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 4.6: 43.6 (#23), Llama 3.1-405B: —
| Benchmark | Grok 4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 33.2% | — |
| Furniture Assembly | 40% | — |
| LMArena Document | 1452 | — |
Multilingual Grok 4.6 leads
Grok 4.6: 53.0 (#74), Llama 3.1-405B: 40.7 (#214)
| Benchmark | Grok 4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1420 | 1248 |
| LMArena Chinese | 1480 | 1242 |
| LMArena French | 1461 | 1279 |
| LMArena German | 1431 | 1252 |
| LMArena Japanese | 1376 | 1208 |
| LMArena Korean | 1397 | 1184 |
| LMArena Russian | 1422 | 1265 |
| LMArena Spanish | 1404 | 1260 |
Instruction Following Grok 4.6 leads
Grok 4.6: 75.4 (#63), Llama 3.1-405B: 65.9 (#214)
| Benchmark | Grok 4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1431 | 1259 |
| IFEval | — | 81.1% |
Long Context Grok 4.6 leads
Grok 4.6: 44.5 (#66), Llama 3.1-405B: 38.4 (#197)
| Benchmark | Grok 4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1454 | 1266 |
Writing & Preference Grok 4.6 leads
Grok 4.6: 62.3 (#80), Llama 3.1-405B: 38.9 (#251)
| Benchmark | Grok 4.6 | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1428 | 1284 |
| LMArena Creative Writing | 1428 | 1262 |
| LMArena Multi-Turn | 1425 | 1297 |
| EQ-Bench Creative Writing | — | 870 |
| WildBench | — | 78.3% |
Frequently asked questions
Is Grok 4.6 better than Llama 3.1-405B?
Grok 4.6 is the stronger model overall, scoring 56.9 to 30.7 on the Noometry Index.
Is Grok 4.6 or Llama 3.1-405B better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 33.1 in the Noometry coding category.
How many benchmarks do Grok 4.6 and Llama 3.1-405B share?
23 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and Llama 3.1-405B has 42.