Loading data...
Nemotron-Flash-3B: benchmark results
Provider: NVIDIA. Access: Open.
Aggregate Rating 1394 ± 37, rank #6435 of 10552 rated models, from 26 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
| Lara Mini Base Report (base-model protocol) - MATH (4-shot) | 67.7 | Math-Verify equivalence, Minerva prompts, 5,000 problems ove | 98.1 |
| Lara Mini Base Report (base-model protocol) - MBPP+ (3-shot) | 58.7 | pass@1; must pass MBPP's own and the EvalPlus tests (%) | 88 |
| Lara Mini Base Report (base-model protocol) - XNLI (English) (0-shot) | 55.2 | Accuracy (%), English benchmark | 87 |
| Lara Mini Base Report (base-model protocol) - PIQA (0-shot) | 80 | Accuracy normalized by answer length (%), English benchmark | 86.1 |
| Lara Mini Base Report (base-model protocol) - MMLU-Pro (5 (CoT)-shot) | 39.3 | Exact match (%), English benchmark | 85.2 |
| Lara Mini Base Report (base-model protocol) - MBPP (3-shot) | 52.2 | pass@1 (execution) (%) | 79.6 |
| Lara Mini Base Report (base-model protocol) - MGSM (8 (CoT)-shot) | 46.1 | Exact match on each language's native CoT answer phrase, ave | 75.9 |
| Lara Mini Base Report (base-model protocol) - GSM8K (5-shot) | 65.4 | Exact match (strict extraction: first "#### N", else first \ | 68.5 |
| Lara Mini Base Report (base-model protocol) - ARC-Challenge (25-shot) | 57.3 | Accuracy normalized by answer length (%), English benchmark | 63 |
| Lara Mini Base Report (base-model protocol) - Belebele (English) (0-shot) | 70.8 | Accuracy (%), English benchmark | 63 |
| Lara Mini Base Report (base-model protocol) - PAWS-X, All Languages (0-shot) | 56 | Accuracy (%) averaged over all languages/variants of the ben | 63 |
| Lara Mini Base Report (base-model protocol) - PAWS (English) (0-shot) | 65.6 | Accuracy (%), English benchmark | 62 |
Interactive version: theaggregate.ai/model?slug=nemotron-flash-3b · How It Works · Data refreshed daily, snapshot 2026-11-16.