Llama-3.1-SuperNova-Lite: benchmark results
Arcee AI's Llama 3.1 8B distilled from Llama 3.1 405B Instruct logits, tuned for strong instruction following at low cost. Provider: Meta. Released 2024-09-10. Access: Open.
Unified ELO 1531 ± 1, rank #541 of 1392 rated models, from 24 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EVALITA - faq | 54.89 | CPS | 97.9 |
| Open CoT - LSAT Analytical Reasoning | 13.91 | CoT Gain (%) | 97.7 |
| Open LLM Leaderboard - IFEval | 80.17 | Score | 97.5 |
| Open Korean LLM Leaderboard | 48.88 | Average Score (%) | 96.4 |
| EVALITA - evalita NER | 39.49 | CPS | 95.7 |
| Open CoT - LSAT Logical Reasoning | 20.59 | CoT Gain (%) | 95 |
| Open CoT Leaderboard | 13.97 | Average CoT Gain (%) | 91.6 |
| Open CoT - LogiQA 2 | 12.66 | CoT Gain (%) | 81.3 |
| Open CoT - LSAT Reading Comprehension | 18.22 | CoT Gain (%) | 77.5 |
| EVALITA - sentiment-analysis | 75.24 | CPS | 72.3 |
| Open LLM Leaderboard - MMLU-Pro | 31.97 | Score | 69.5 |
| Open LLM Leaderboard - MATH Level 5 | 18.28 | Score | 67.9 |
Interactive version: theaggregate.ai/model?slug=llama-3-1-supernova-lite · How It Works · Data refreshed daily, snapshot 2026-09-05.