Model comparison
Nemotron-4 15B vs Qwen2.5-Coder (1.5B)
Neither Nemotron-4 15B nor Qwen2.5-Coder (1.5B) has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 6 shared benchmarks.
NVIDIA
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both.
- Qwen2.5-Coder (1.5B) has downloadable open weights; the other is API-only.
Side by side
| Nemotron-4 15B | Qwen2.5-Coder (1.5B) | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | — | — |
| Released | 2024-02-26 | 2024-09-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 8 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Reasoning Not comparable
Nemotron-4 15B: —, Qwen2.5-Coder (1.5B): —
| Benchmark | Nemotron-4 15B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| Epoch Capabilities Index | 107.72 | 113.14 |
| HellaSwag | 82.4% | 76.8% |
| WinoGrande | 78% | 72.9% |
| BIG-Bench Hard | 58.7% | — |
| PIQA | 82.4% | — |
Math Not comparable
Nemotron-4 15B: —, Qwen2.5-Coder (1.5B): —
| Benchmark | Nemotron-4 15B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| GSM8K | 46% | 86.7% |
Knowledge Not comparable
Nemotron-4 15B: —, Qwen2.5-Coder (1.5B): —
| Benchmark | Nemotron-4 15B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| ARC (AI2) Challenge | 55.5% | 60.9% |
| MMLU | 58.7% | 68% |
Frequently asked questions
Is Nemotron-4 15B better than Qwen2.5-Coder (1.5B)?
Neither Nemotron-4 15B nor Qwen2.5-Coder (1.5B) 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 Qwen2.5-Coder (1.5B) share?
6 benchmarks have published results for both models. Nemotron-4 15B has 8 scored results on Noometry and Qwen2.5-Coder (1.5B) has 6.