Model comparison
Llama 2-13B vs Nemotron-4 15B
Llama 2-13B has enough public results to be ranked (#309); Nemotron-4 15B does not yet, so treat this comparison as directional.
Last verified . 8 shared benchmarks.
Meta
NVIDIASummary
- They share 8 benchmarks with published results for both.
- Llama 2-13B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-13B | Nemotron-4 15B | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 29.6 | — |
| Released | 2023-07-18 | 2024-02-26 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 2-13B: 30.9 (#291), Nemotron-4 15B: —
| Benchmark | Llama 2-13B | Nemotron-4 15B |
|---|---|---|
| LMArena Coding | 1062 | — |
Reasoning Not comparable
Llama 2-13B: 12.8 (#337), Nemotron-4 15B: —
| Benchmark | Llama 2-13B | Nemotron-4 15B |
|---|---|---|
| BIG-Bench Hard | 58.2% | 58.7% |
| Epoch Capabilities Index | 106.17 | 107.72 |
| HellaSwag | 80.7% | 82.4% |
| PIQA | 80.8% | 82.4% |
| WinoGrande | 72.8% | 78% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1051 | — |
| DTBench | 42.2% | — |
| LAMBADA | 76.5% | — |
Math Not comparable
Llama 2-13B: 31.1 (#229), Nemotron-4 15B: —
| Benchmark | Llama 2-13B | Nemotron-4 15B |
|---|---|---|
| GSM8K | 36.9% | 46% |
| LMArena Math | 1065 | — |
Knowledge Not comparable
Llama 2-13B: 28.1 (#249), Nemotron-4 15B: —
| Benchmark | Llama 2-13B | Nemotron-4 15B |
|---|---|---|
| ARC (AI2) Challenge | 60.3% | 55.5% |
| MMLU | 55.6% | 58.7% |
| LMArena Expert | 1030 | — |
| BoolQ | 82.4% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Nemotron-4 15B: —
| Benchmark | Llama 2-13B | Nemotron-4 15B |
|---|---|---|
| ScienceQA | 55.8% | — |
Multilingual Not comparable
Llama 2-13B: 26.5 (#279), Nemotron-4 15B: —
| Benchmark | Llama 2-13B | Nemotron-4 15B |
|---|---|---|
| LMArena Non-English | 1024 | — |
| LMArena Chinese | 1001 | — |
| LMArena French | 1044 | — |
| LMArena German | 1009 | — |
| LMArena Japanese | 894 | — |
| LMArena Korean | 953 | — |
| LMArena Russian | 1055 | — |
| LMArena Spanish | 1087 | — |
Instruction Following Not comparable
Llama 2-13B: 53.3 (#287), Nemotron-4 15B: —
| Benchmark | Llama 2-13B | Nemotron-4 15B |
|---|---|---|
| LMArena Instruction Following | 1045 | — |
Long Context Not comparable
Llama 2-13B: 32.3 (#269), Nemotron-4 15B: —
| Benchmark | Llama 2-13B | Nemotron-4 15B |
|---|---|---|
| LMArena Longer Query | 1064 | — |
Writing & Preference Not comparable
Llama 2-13B: 29.8 (#289), Nemotron-4 15B: —
| Benchmark | Llama 2-13B | Nemotron-4 15B |
|---|---|---|
| LMArena Text | 1084 | — |
| LMArena Creative Writing | 1047 | — |
| LMArena Multi-Turn | 1050 | — |
Frequently asked questions
Is Llama 2-13B better than Nemotron-4 15B?
Llama 2-13B has enough public results to be ranked (#309); Nemotron-4 15B does not yet, so treat this comparison as directional.
How many benchmarks do Llama 2-13B and Nemotron-4 15B share?
8 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Nemotron-4 15B has 8.