Model comparison
Llama 3.2 3B vs Nemotron-4 15B
Llama 3.2 3B has enough public results to be ranked (#321); Nemotron-4 15B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Meta
NVIDIASummary
- Llama 3.2 3B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.2 3B | Nemotron-4 15B | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 28.9 | — |
| Released | 2024-09-24 | 2024-02-26 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 18 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 3B: 27.6 (#319), Nemotron-4 15B: —
| Benchmark | Llama 3.2 3B | Nemotron-4 15B |
|---|---|---|
| BigCodeBench Instruct | 23.4% | — |
| LMArena Coding | 1098 | — |
| BigCodeBench Complete | 28.3% | — |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 20.1 (#143), Nemotron-4 15B: —
| Benchmark | Llama 3.2 3B | Nemotron-4 15B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |
Reasoning Not comparable
Llama 3.2 3B: 21.0 (#228), Nemotron-4 15B: —
| Benchmark | Llama 3.2 3B | Nemotron-4 15B |
|---|---|---|
| LMArena Hard Prompts | 1095 | — |
| BIG-Bench Hard | — | 58.7% |
| Epoch Capabilities Index | — | 107.72 |
| HellaSwag | — | 82.4% |
| PIQA | — | 82.4% |
| WinoGrande | — | 78% |
Math Not comparable
Llama 3.2 3B: 32.4 (#214), Nemotron-4 15B: —
| Benchmark | Llama 3.2 3B | Nemotron-4 15B |
|---|---|---|
| LMArena Math | 1126 | — |
| GSM8K | — | 46% |
Knowledge Not comparable
Llama 3.2 3B: 29.7 (#235), Nemotron-4 15B: —
| Benchmark | Llama 3.2 3B | Nemotron-4 15B |
|---|---|---|
| LMArena Expert | 1090 | — |
| ARC (AI2) Challenge | — | 55.5% |
| MMLU | — | 58.7% |
Multilingual Not comparable
Llama 3.2 3B: 26.2 (#281), Nemotron-4 15B: —
| Benchmark | Llama 3.2 3B | Nemotron-4 15B |
|---|---|---|
| LMArena Non-English | 1019 | — |
| LMArena Chinese | 1017 | — |
| LMArena German | 1056 | — |
| LMArena Russian | 949 | — |
Instruction Following Not comparable
Llama 3.2 3B: 56.0 (#275), Nemotron-4 15B: —
| Benchmark | Llama 3.2 3B | Nemotron-4 15B |
|---|---|---|
| LMArena Instruction Following | 1089 | — |
Long Context Not comparable
Llama 3.2 3B: 33.4 (#261), Nemotron-4 15B: —
| Benchmark | Llama 3.2 3B | Nemotron-4 15B |
|---|---|---|
| LMArena Longer Query | 1100 | — |
Writing & Preference Not comparable
Llama 3.2 3B: 24.7 (#307), Nemotron-4 15B: —
| Benchmark | Llama 3.2 3B | Nemotron-4 15B |
|---|---|---|
| LMArena Text | 1110 | — |
| LMArena Creative Writing | 1094 | — |
| EQ-Bench Creative Writing | 595 | — |
| LMArena Multi-Turn | 1105 | — |
Frequently asked questions
Is Llama 3.2 3B better than Nemotron-4 15B?
Llama 3.2 3B has enough public results to be ranked (#321); Nemotron-4 15B does not yet, so treat this comparison as directional.
How many benchmarks do Llama 3.2 3B and Nemotron-4 15B share?
0 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Nemotron-4 15B has 8.