Model comparison
Nemotron-4 15B vs Qwen-14B
Qwen-14B has enough public results to be ranked (#273); Nemotron-4 15B does not yet, so treat this comparison as directional.
Last verified . 6 shared benchmarks.
NVIDIA
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| Nemotron-4 15B | Qwen-14B | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | — | 30.8 |
| Released | 2024-02-26 | 2023-09-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 8 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Nemotron-4 15B: —, Qwen-14B: 30.6 (#283)
| Benchmark | Nemotron-4 15B | Qwen-14B |
|---|---|---|
| LMArena Coding | — | 1072 |
Reasoning Not comparable
Nemotron-4 15B: —, Qwen-14B: 18.7 (#255)
| Benchmark | Nemotron-4 15B | Qwen-14B |
|---|---|---|
| BIG-Bench Hard | 58.7% | 55% |
| Epoch Capabilities Index | 107.38 | 112.8 |
| PIQA | 82.4% | 79.9% |
| LMArena Hard Prompts | — | 1027 |
| HellaSwag | 82.4% | — |
| LAMBADA | — | 71.1% |
| WinoGrande | 78% | — |
Math Not comparable
Nemotron-4 15B: —, Qwen-14B: 28.7 (#224)
| Benchmark | Nemotron-4 15B | Qwen-14B |
|---|---|---|
| GSM8K | 46% | 61.3% |
| LMArena Math | — | 1068 |
Knowledge Not comparable
Nemotron-4 15B: —, Qwen-14B: —
| Benchmark | Nemotron-4 15B | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | 55.5% | 84.4% |
| MMLU | 58.7% | 66.3% |
| BoolQ | — | 86.2% |
Multilingual Not comparable
Nemotron-4 15B: —, Qwen-14B: 27.7 (#270)
| Benchmark | Nemotron-4 15B | Qwen-14B |
|---|---|---|
| LMArena Non-English | — | 1042 |
| LMArena Chinese | — | 1077 |
Instruction Following Not comparable
Nemotron-4 15B: —, Qwen-14B: 52.6 (#284)
| Benchmark | Nemotron-4 15B | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | — | 1031 |
Long Context Not comparable
Nemotron-4 15B: —, Qwen-14B: 31.3 (#276)
| Benchmark | Nemotron-4 15B | Qwen-14B |
|---|---|---|
| LMArena Longer Query | — | 1029 |
Writing & Preference Not comparable
Nemotron-4 15B: —, Qwen-14B: 27.8 (#294)
| Benchmark | Nemotron-4 15B | Qwen-14B |
|---|---|---|
| LMArena Text | — | 1051 |
| LMArena Creative Writing | — | 1028 |
| LMArena Multi-Turn | — | 1022 |
Frequently asked questions
Is Nemotron-4 15B better than Qwen-14B?
Qwen-14B has enough public results to be ranked (#273); Nemotron-4 15B does not yet, so treat this comparison as directional.
How many benchmarks do Nemotron-4 15B and Qwen-14B share?
6 benchmarks have published results for both models. Nemotron-4 15B has 8 scored results on Noometry and Qwen-14B has 18.