Model comparison
Llama 2-70B vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 24.4 on the Noometry Index.
Last verified . 15 shared benchmarks.
Meta
NVIDIASummary
- They share 15 benchmarks with published results for both. Llama 2-70B scores higher in 0 categories and Nemotron 3 Super in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Nemotron 3 Super leads 39.6 to 8.1.
Side by side
| Llama 2-70B | Nemotron 3 Super | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 24.4 | 40.1 |
| Released | 2023-07-18 | 2026-03-11 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.08 |
| Output $ / M tokens | — | $0.45 |
| Results tracked | 35 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
Llama 2-70B: 31.4 (#286), Nemotron 3 Super: 39.4 (#158)
| Benchmark | Llama 2-70B | Nemotron 3 Super |
|---|---|---|
| LMArena Coding | 1079 | 1403 |
| SciCode | — | 36% |
| WeirdML | — | 38% |
| ALE-Bench | — | 213.9 |
Reasoning Nemotron 3 Super leads
Llama 2-70B: 14.4 (#325), Nemotron 3 Super: 18.7 (#276)
| Benchmark | Llama 2-70B | Nemotron 3 Super |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1386 |
| NYT Connections (extended) | — | 15.4% |
| CritPt | — | 3.1% |
| DTBench | 41.6% | — |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| Epoch Capabilities Index | 113.79 | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |
Math Nemotron 3 Super leads
Llama 2-70B: 8.1 (#326), Nemotron 3 Super: 39.6 (#101)
| Benchmark | Llama 2-70B | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1091 | 1380 |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 0% | — |
| MATH Level 5 | 3.3% | — |
| GSM8K | 69.6% | — |
Knowledge Nemotron 3 Super leads
Llama 2-70B: 7.4 (#310), Nemotron 3 Super: 38.9 (#139)
| Benchmark | Llama 2-70B | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1039 | 1398 |
| GPQA Diamond | 26.3% | — |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual Nemotron 3 Super leads
Llama 2-70B: 27.7 (#274), Nemotron 3 Super: 48.4 (#144)
| Benchmark | Llama 2-70B | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1045 | 1355 |
| LMArena Chinese | 995 | 1432 |
| LMArena French | 1090 | 1405 |
| LMArena German | 1041 | 1341 |
| LMArena Russian | 1083 | 1336 |
| LMArena Spanish | 1143 | 1417 |
| LMArena Japanese | 927 | — |
| LMArena Korean | 964 | — |
Instruction Following Nemotron 3 Super leads
Llama 2-70B: 54.9 (#278), Nemotron 3 Super: 71.2 (#154)
| Benchmark | Llama 2-70B | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1071 | 1347 |
Long Context Nemotron 3 Super leads
Llama 2-70B: 32.3 (#270), Nemotron 3 Super: 41.5 (#139)
| Benchmark | Llama 2-70B | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1062 | 1362 |
Writing & Preference Nemotron 3 Super leads
Llama 2-70B: 32.3 (#279), Nemotron 3 Super: 55.9 (#140)
| Benchmark | Llama 2-70B | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1115 | 1378 |
| LMArena Creative Writing | 1075 | 1317 |
| LMArena Multi-Turn | 1088 | 1369 |
Frequently asked questions
Is Llama 2-70B better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 24.4 on the Noometry Index.
Is Llama 2-70B or Nemotron 3 Super better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 31.4 in the Noometry coding category.
How many benchmarks do Llama 2-70B and Nemotron 3 Super share?
15 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Nemotron 3 Super has 21.