Model comparison
Nemotron-4 15B vs StarCoder 2 7B
Neither Nemotron-4 15B nor StarCoder 2 7B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 5 shared benchmarks.
Summary
- They share 5 benchmarks with published results for both.
- StarCoder 2 7B has downloadable open weights; the other is API-only.
Side by side
| Nemotron-4 15B | StarCoder 2 7B | |
|---|---|---|
| Provider | NVIDIA | NVIDIA |
| Noometry Index | — | 37.0 |
| Released | 2024-02-26 | 2024-02-20 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 8 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Nemotron-4 15B: —, StarCoder 2 7B: 34.8
| Benchmark | Nemotron-4 15B | StarCoder 2 7B |
|---|---|---|
| BigCodeBench Complete | — | 27.7% |
| HumanEval+ | — | 29.9% |
Reasoning Not comparable
Nemotron-4 15B: —, StarCoder 2 7B: —
| Benchmark | Nemotron-4 15B | StarCoder 2 7B |
|---|---|---|
| Epoch Capabilities Index | 107.72 | 93.56 |
| WinoGrande | 78% | 57.1% |
| BIG-Bench Hard | 58.7% | — |
| HellaSwag | 82.4% | — |
| PIQA | 82.4% | — |
Math Not comparable
Nemotron-4 15B: —, StarCoder 2 7B: —
| Benchmark | Nemotron-4 15B | StarCoder 2 7B |
|---|---|---|
| GSM8K | 46% | 32.7% |
Knowledge Not comparable
Nemotron-4 15B: —, StarCoder 2 7B: —
| Benchmark | Nemotron-4 15B | StarCoder 2 7B |
|---|---|---|
| ARC (AI2) Challenge | 55.5% | 38.7% |
| MMLU | 58.7% | 38.8% |
Frequently asked questions
Is Nemotron-4 15B better than StarCoder 2 7B?
Neither Nemotron-4 15B nor StarCoder 2 7B has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do Nemotron-4 15B and StarCoder 2 7B share?
5 benchmarks have published results for both models. Nemotron-4 15B has 8 scored results on Noometry and StarCoder 2 7B has 7.