NAPS-llama-3.1-8B-instruct-v0.3.2: benchmark results
Provider: Other. Access: Open.
Unified ELO 1450 ± 17, rank #1529 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GSM8K (flexible extract) | 56.71 | Exact match, flexible extract (%) | 90.6 |
| Open Korean LLM - Ko-IFEval | 41.78 | Strict accuracy, prompt/instruction mean (%) | 85.2 |
| Open Korean LLM - Ko-EQ-Bench | 29.17 | EQ-Bench score | 77.3 |
| Open Ko-LLM Leaderboard | 37.16 | Average (%) | 61 |
| Open Korean LLM Leaderboard | 37.16 | Average Score (%) | 61 |
| Open Korean LLM - KorNAT-CKA | 25.15 | Normalized accuracy (%) | 55.4 |
| Open Korean LLM - KorNAT-Harmless | 63.09 | Normalized accuracy (%) | 55.4 |
| Open Korean LLM - KorNAT-Helpful | 46.77 | Normalized accuracy (%) | 49.1 |
| Open Korean LLM - Ko-Winogrande | 57.14 | Accuracy (%) | 29.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
Interactive version: theaggregate.ai/model?slug=naps-llama-3-1-8b-instruct-v0-3-2 · How It Works · Data refreshed daily, snapshot 2026-09-19.