MBPP#1 of 28
pass@1
View run →94.0%±1.1%
Evaluated across 13 benchmarks. Ranks in the top 3 on 2 of 13. Strongest showing on MBPP (94.0% pass@1, #1 of 28). Weakest on MBPP(Instruct) (0.0% pass@1, #20 of 24).
| Benchmark | Metric | Score | Rank | Actions |
|---|---|---|---|---|
| MBPP | pass@1 | 94.0%±1.1% | #1 of 28 | View run → |
| IFEval | prompt_level_strict_acc | 88.4%±1.4% | #6 of 28 | View run → |
| GSM8K | exact_match | 86.1%±1.0% | #9 of 28 | View run → |
| MMLU-Pro | exact_match | 80.5%±0.3% | #5 of 28 | View run → |
| MGSM | exact_match | 79.4%±0.7% | #2 of 28 | View run → |
| EQ-Bench | eqbench | 78.3±1.8 | #12 of 28 | View run → |
| MMLU | acc | 36.2%±0.4% | #25 of 28 | View run → |
| LongBench | score | 35.2%±0.4% | #7 of 10 | View run → |
| GPQA Diamond | acc | 29.8%±3.3% | #11 of 28 | View run → |
| GPQA Main | acc | 29.5%±2.2% | #12 of 28 | View run → |
| GPQA Extended | acc | 26.6%±1.9% | #19 of 28 | View run → |
| BBH | exact_match | 18.1%±0.4% | #16 of 28 | View run → |
| MBPP(Instruct) | pass@1 | 0.0%±0.0% | #20 of 24 | View run → |
Citation
FrozeBench. "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4." https://frozebench.com/models/nvidia-nvidia-nemotron-3-super-120b-a12b-nvfp4. Retrieved 2026-06-04.
BibTeX
@misc{frozebench_nvidia_NVIDIA_Nemotron_3_Super_120B_A12B_NVFP4,
title = {nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4},
howpublished = {\url{https://frozebench.com/models/nvidia-nvidia-nemotron-3-super-120b-a12b-nvfp4}},
year = {2026},
note = {FrozeBench. Retrieved 2026-06-04.}
}URL
https://frozebench.com/models/nvidia-nvidia-nemotron-3-super-120b-a12b-nvfp4