Model comparison
Nemotron-4 15B vs Qwen2.5 7B Instruct
Qwen2.5 7B Instruct has enough public results to be ranked (#320); Nemotron-4 15B does not yet, so treat this comparison as directional.
Last verified . 2 shared benchmarks.
NVIDIA
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both.
- Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.
Side by side
| Nemotron-4 15B | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | — | 29.0 |
| Released | 2024-02-26 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.17 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 8 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Nemotron-4 15B: —, Qwen2.5 7B Instruct: 36.5 (#208)
| Benchmark | Nemotron-4 15B | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| BigCodeBench Complete | — | 46.1% |
Agentic & Tool Use Not comparable
Nemotron-4 15B: —, Qwen2.5 7B Instruct: 23.8 (#124)
| Benchmark | Nemotron-4 15B | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning Not comparable
Nemotron-4 15B: —, Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | Nemotron-4 15B | Qwen2.5 7B Instruct |
|---|---|---|
| Epoch Capabilities Index | 107.72 | 118.51 |
| Chess Puzzles | — | 0% |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
| BIG-Bench Hard | 58.7% | — |
| HellaSwag | 82.4% | — |
| PIQA | 82.4% | — |
| WinoGrande | 78% | — |
Math Not comparable
Nemotron-4 15B: —, Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | Nemotron-4 15B | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| Omni-MATH | — | 29.4% |
| GSM8K | 46% | — |
Knowledge Not comparable
Nemotron-4 15B: —, Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | Nemotron-4 15B | Qwen2.5 7B Instruct |
|---|---|---|
| MMLU | 58.7% | 72.9% |
| GPQA Diamond | — | 35.5% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| ARC (AI2) Challenge | 55.5% | — |
Instruction Following Not comparable
Nemotron-4 15B: —, Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | Nemotron-4 15B | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
Writing & Preference Not comparable
Nemotron-4 15B: —, Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | Nemotron-4 15B | Qwen2.5 7B Instruct |
|---|---|---|
| WildBench | — | 73.1% |
Frequently asked questions
Is Nemotron-4 15B better than Qwen2.5 7B Instruct?
Qwen2.5 7B Instruct has enough public results to be ranked (#320); Nemotron-4 15B does not yet, so treat this comparison as directional.
How many benchmarks do Nemotron-4 15B and Qwen2.5 7B Instruct share?
2 benchmarks have published results for both models. Nemotron-4 15B has 8 scored results on Noometry and Qwen2.5 7B Instruct has 15.