Model comparison
Gemma 2B vs Nemotron-4 15B
Gemma 2B has enough public results to be ranked (#305); Nemotron-4 15B does not yet, so treat this comparison as directional.
Last verified . 8 shared benchmarks.
Google
NVIDIASummary
- They share 8 benchmarks with published results for both.
- Gemma 2B has downloadable open weights; the other is API-only.
Side by side
| Gemma 2B | Nemotron-4 15B | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 29.1 | — |
| Released | 2024-02-21 | 2024-02-26 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemma 2B: 28.9 (#300), Nemotron-4 15B: —
| Benchmark | Gemma 2B | Nemotron-4 15B |
|---|---|---|
| LMArena Coding | 1010 | — |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning Not comparable
Gemma 2B: 17.9 (#275), Nemotron-4 15B: —
| Benchmark | Gemma 2B | Nemotron-4 15B |
|---|---|---|
| BIG-Bench Hard | 35.2% | 58.7% |
| Epoch Capabilities Index | 93.57 | 107.38 |
| HellaSwag | 71.4% | 82.4% |
| PIQA | 77.3% | 82.4% |
| WinoGrande | 65.4% | 78% |
| LMArena Hard Prompts | 989 | — |
Math Not comparable
Gemma 2B: 27.6 (#237), Nemotron-4 15B: —
| Benchmark | Gemma 2B | Nemotron-4 15B |
|---|---|---|
| GSM8K | 17.7% | 46% |
| LMArena Math | 1009 | — |
Knowledge Not comparable
Gemma 2B: —, Nemotron-4 15B: —
| Benchmark | Gemma 2B | Nemotron-4 15B |
|---|---|---|
| ARC (AI2) Challenge | 42.1% | 55.5% |
| MMLU | 42.3% | 58.7% |
| BoolQ | 69.4% | — |
| TriviaQA | 53.2% | — |
Multilingual Not comparable
Gemma 2B: 23.1 (#289), Nemotron-4 15B: —
| Benchmark | Gemma 2B | Nemotron-4 15B |
|---|---|---|
| LMArena Non-English | 958 | — |
| LMArena Chinese | 986 | — |
| LMArena Russian | 937 | — |
Instruction Following Not comparable
Gemma 2B: 48.8 (#297), Nemotron-4 15B: —
| Benchmark | Gemma 2B | Nemotron-4 15B |
|---|---|---|
| LMArena Instruction Following | 971 | — |
Long Context Not comparable
Gemma 2B: 29.9 (#286), Nemotron-4 15B: —
| Benchmark | Gemma 2B | Nemotron-4 15B |
|---|---|---|
| LMArena Longer Query | 981 | — |
Writing & Preference Not comparable
Gemma 2B: 24.1 (#303), Nemotron-4 15B: —
| Benchmark | Gemma 2B | Nemotron-4 15B |
|---|---|---|
| LMArena Text | 1002 | — |
| LMArena Creative Writing | 986 | — |
| LMArena Multi-Turn | 945 | — |
Frequently asked questions
Is Gemma 2B better than Nemotron-4 15B?
Gemma 2B has enough public results to be ranked (#305); Nemotron-4 15B does not yet, so treat this comparison as directional.
How many benchmarks do Gemma 2B and Nemotron-4 15B share?
8 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Nemotron-4 15B has 8.