Mistral-NeMo-Minitron-8B-Instruct: benchmark results
NVIDIA's instruct-aligned version of Mistral-NeMo-Minitron-8B-Base, tuned with NeMo Aligner for chat, RAG, and function calling (8K context). Provider: NVIDIA. Released 2024-10-02. Access: Open.
Aggregate Rating 1466 ± 37, rank #907 of 1656 rated models, from 72 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Enkrypt AI - Bias Risk | 7.49 | Risk Score | 99.7 |
| Enkrypt AI - Safety Risk | 3.67 | Risk Score | 99.7 |
| Enkrypt AI - Toxicity Risk | 0 | Risk Score | 98.5 |
| Enkrypt AI - Risk Score | 13.99 | Risk Score | 97 |
| LatamBoard - Spanish PAWS | 63 | Score (%) | 86.4 |
| EuroEval Spanish NLU - Sentiment Headlines ES | 48.9 | Matthews correlation coefficient (%) | 85 |
| LatamBoard - Spanish OpenBookQA | 38 | Score (%) | 84.8 |
| LatamBoard - BLUEX | 61.34 | Score (%) | 81.8 |
| LatamBoard - ENEM Challenge | 73.41 | Score (%) | 81.8 |
| LatamBoard - Spanish COPA | 83.6 | Score (%) | 81.8 |
| Enkrypt AI - Insecure Code Risk | 10.22 | Risk Score | 79.4 |
| LatamBoard - Spanish XNLI | 47.83 | Score (%) | 78.8 |
Interactive version: theaggregate.ai/model?slug=mistral-nemo-minitron-8b-instruct · How It Works · Data refreshed daily, snapshot 2026-10-20.