Model comparison
Grok 4.1 vs Llama 3-70B
Grok 4.1 is the stronger model overall, scoring 40.8 to 28.5 on the Noometry Index.
Last verified . 18 shared benchmarks.
MetaSummary
- They share 18 benchmarks with published results for both. Grok 4.1 scores higher in 8 categories and Llama 3-70B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.1 leads 36.2 to 12.0.
- The biggest single-benchmark swing is Cybench: 39% for Grok 4.1 and 5% for Llama 3-70B.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| Grok 4.1 | Llama 3-70B | |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 40.8 | 28.5 |
| Released | 2025-11-17 | 2024-04-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Grok 4.1: 33.4 (#246), Llama 3-70B: 35.3 (#215)
| Benchmark | Grok 4.1 | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1445 | 1206 |
| LMArena WebDev | 1214 | — |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Grok 4.1 leads
Grok 4.1: 33.8 (#47), Llama 3-70B: 20.9 (#132)
| Benchmark | Grok 4.1 | Llama 3-70B |
|---|---|---|
| Cybench | 39% | 5% |
Reasoning Grok 4.1 leads
Grok 4.1: 28.3 (#91), Llama 3-70B: 17.4 (#284)
| Benchmark | Grok 4.1 | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1436 | 1195 |
| Kagi LLM Benchmark | — | 35.1% |
| DTBench | — | 54.2% |
| Epoch Capabilities Index | — | 122.91 |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math Grok 4.1 leads
Grok 4.1: 36.2 (#124), Llama 3-70B: 12.0 (#299)
| Benchmark | Grok 4.1 | Llama 3-70B |
|---|---|---|
| LMArena Math | 1422 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| MATH Level 5 | — | 22.6% |
Knowledge Grok 4.1 leads
Grok 4.1: 38.9 (#129), Llama 3-70B: 20.8 (#272)
| Benchmark | Grok 4.1 | Llama 3-70B |
|---|---|---|
| LMArena Expert | 1417 | 1149 |
| GPQA Diamond | — | 40.6% |
| MMLU | — | 79.3% |
Multilingual Grok 4.1 leads
Grok 4.1: 53.6 (#64), Llama 3-70B: 33.8 (#246)
| Benchmark | Grok 4.1 | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1425 | 1142 |
| LMArena Chinese | 1464 | 1114 |
| LMArena French | 1448 | 1231 |
| LMArena German | 1447 | 1169 |
| LMArena Japanese | 1396 | 1017 |
| LMArena Korean | 1407 | 1017 |
| LMArena Russian | 1434 | 1159 |
| LMArena Spanish | 1438 | 1241 |
Instruction Following Grok 4.1 leads
Grok 4.1: 74.0 (#106), Llama 3-70B: 62.8 (#233)
| Benchmark | Grok 4.1 | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1400 | 1194 |
Long Context Grok 4.1 leads
Grok 4.1: 43.2 (#96), Llama 3-70B: 35.6 (#235)
| Benchmark | Grok 4.1 | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1416 | 1174 |
Writing & Preference Grok 4.1 leads
Grok 4.1: 62.6 (#71), Llama 3-70B: 43.0 (#225)
| Benchmark | Grok 4.1 | Llama 3-70B |
|---|---|---|
| LMArena Text | 1437 | 1221 |
| LMArena Creative Writing | 1411 | 1210 |
| LMArena Multi-Turn | 1438 | 1223 |
Frequently asked questions
Is Grok 4.1 better than Llama 3-70B?
Grok 4.1 is the stronger model overall, scoring 40.8 to 28.5 on the Noometry Index.
Is Grok 4.1 or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.3 versus 33.4 in the Noometry coding category.
How many benchmarks do Grok 4.1 and Llama 3-70B share?
18 benchmarks have published results for both models. Grok 4.1 has 19 scored results on Noometry and Llama 3-70B has 31.