Model comparison
Grok 4.20 (Non-Reasoning) vs Llama 2-70B
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 24.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
MetaSummary
- They share 22 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 8 categories and Llama 2-70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.20 (Non-Reasoning) leads 52.8 to 7.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 92.2% for Grok 4.20 (Non-Reasoning) and 0% for Llama 2-70B.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| Grok 4.20 (Non-Reasoning) | Llama 2-70B | |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 48.6 | 24.4 |
| Released | 2026-02-17 | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 30K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 46 | 35 |
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 2-70B: 31.4 (#286)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1459 | 1079 |
| LMArena WebDev | 1375 | — |
| WeirdML | 52.3% | — |
| ALE-Bench | 1,150 | — |
Agentic & Tool Use Not comparable
Grok 4.20 (Non-Reasoning): 34.4 (#46), Llama 2-70B: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 2-70B |
|---|---|---|
| Terminal-Bench | 57.3% | — |
| τ²-bench Banking | 18% | — |
| LMArena Search | 1189 | — |
| Vending-Bench 2 | 4,663 | — |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.3 (#32), Llama 2-70B: 14.4 (#325)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1073 |
| DTBench | 90.1% | 41.6% |
| Epoch Capabilities Index | 151.98 | 113.79 |
| ForecastBench | 61.4 | 51.4 |
| ARC-AGI-2 | 65.1% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 85.4% | — |
| ARC-AGI-1 | 89.5% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 63.8% | — |
| LMCA | 38.7% | — |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 48.2 (#65), Llama 2-70B: 8.1 (#326)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 2-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 92.2% | 0% |
| LMArena Math | 1455 | 1091 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 14% | — |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |
Knowledge Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.8 (#60), Llama 2-70B: 7.4 (#310)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 2-70B |
|---|---|---|
| GPQA Diamond | 89.3% | 26.3% |
| LMArena Expert | 1439 | 1039 |
| SimpleQA Verified | 30.2% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multimodal Not comparable
Grok 4.20 (Non-Reasoning): 33.3 (#98), Llama 2-70B: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 2-70B |
|---|---|---|
| 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 2-70B: 27.7 (#274)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1441 | 1045 |
| LMArena Chinese | 1481 | 995 |
| LMArena French | 1476 | 1090 |
| LMArena German | 1465 | 1041 |
| LMArena Japanese | 1449 | 927 |
| LMArena Korean | 1417 | 964 |
| LMArena Russian | 1458 | 1083 |
| LMArena Spanish | 1443 | 1143 |
Instruction Following Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 74.8 (#83), Llama 2-70B: 54.9 (#278)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1420 | 1071 |
Long Context Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 45.5 (#34), Llama 2-70B: 32.3 (#270)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1437 | 1062 |
| 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 2-70B: 32.3 (#279)
| Benchmark | Grok 4.20 (Non-Reasoning) | Llama 2-70B |
|---|---|---|
| LMArena Text | 1451 | 1115 |
| LMArena Creative Writing | 1438 | 1075 |
| LMArena Multi-Turn | 1456 | 1088 |
| EQ-Bench Creative Writing | 1574 | — |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Llama 2-70B?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 24.4 on the Noometry Index.
Is Grok 4.20 (Non-Reasoning) or Llama 2-70B better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 31.4 in the Noometry coding category.
How many benchmarks do Grok 4.20 (Non-Reasoning) and Llama 2-70B share?
22 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Llama 2-70B has 35.