Model comparison
Llama 3-8B vs Nemotron-4 15B
Llama 3-8B has enough public results to be ranked (#338); Nemotron-4 15B does not yet, so treat this comparison as directional.
Last verified . 4 shared benchmarks.
Meta
NVIDIASummary
- They share 4 benchmarks with published results for both.
- Llama 3-8B has downloadable open weights; the other is API-only.
Side by side
| Llama 3-8B | Nemotron-4 15B | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 25.3 | — |
| Released | 2024-04-18 | 2024-02-26 |
| Weights | Open | Proprietary |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.14 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 34 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3-8B: 30.5 (#285), Nemotron-4 15B: —
| Benchmark | Llama 3-8B | Nemotron-4 15B |
|---|---|---|
| BigCodeBench Instruct | 31.9% | — |
| LMArena Coding | 1152 | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Not comparable
Llama 3-8B: 13.8 (#321), Nemotron-4 15B: —
| Benchmark | Llama 3-8B | Nemotron-4 15B |
|---|---|---|
| Epoch Capabilities Index | 116.33 | 107.38 |
| WinoGrande | 75.7% | 78% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1133 | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| BIG-Bench Hard | — | 58.7% |
| ForecastBench | 58.6 | — |
| HellaSwag | — | 82.4% |
| PIQA | — | 82.4% |
Math Not comparable
Llama 3-8B: 8.3 (#317), Nemotron-4 15B: —
| Benchmark | Llama 3-8B | Nemotron-4 15B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| LMArena Math | 1151 | — |
| MATH Level 5 | 6.1% | — |
| GSM8K | — | 46% |
Knowledge Not comparable
Llama 3-8B: 7.8 (#303), Nemotron-4 15B: —
| Benchmark | Llama 3-8B | Nemotron-4 15B |
|---|---|---|
| ARC (AI2) Challenge | 82.8% | 55.5% |
| MMLU | 68.8% | 58.7% |
| GPQA Diamond | 26.1% | — |
| LMArena Expert | 1113 | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Not comparable
Llama 3-8B: 31.0 (#256), Nemotron-4 15B: —
| Benchmark | Llama 3-8B | Nemotron-4 15B |
|---|---|---|
| LMArena Non-English | 1098 | — |
| LMArena Chinese | 1076 | — |
| LMArena French | 1158 | — |
| LMArena German | 1104 | — |
| LMArena Japanese | 967 | — |
| LMArena Korean | 1003 | — |
| LMArena Russian | 1109 | — |
| LMArena Spanish | 1172 | — |
Instruction Following Not comparable
Llama 3-8B: 58.7 (#255), Nemotron-4 15B: —
| Benchmark | Llama 3-8B | Nemotron-4 15B |
|---|---|---|
| LMArena Instruction Following | 1127 | — |
Long Context Not comparable
Llama 3-8B: 34.2 (#246), Nemotron-4 15B: —
| Benchmark | Llama 3-8B | Nemotron-4 15B |
|---|---|---|
| LMArena Longer Query | 1128 | — |
Writing & Preference Not comparable
Llama 3-8B: 37.7 (#251), Nemotron-4 15B: —
| Benchmark | Llama 3-8B | Nemotron-4 15B |
|---|---|---|
| LMArena Text | 1166 | — |
| LMArena Creative Writing | 1150 | — |
| LMArena Multi-Turn | 1152 | — |
Frequently asked questions
Is Llama 3-8B better than Nemotron-4 15B?
Llama 3-8B has enough public results to be ranked (#338); Nemotron-4 15B does not yet, so treat this comparison as directional.
How many benchmarks do Llama 3-8B and Nemotron-4 15B share?
4 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Nemotron-4 15B has 8.