naps-llama-3-1-instruct-v0.5.1: benchmark results
Provider: Other. Access: Open.
Unified ELO 1459 ± 17, rank #1462 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GSM8K (flexible extract) | 44.73 | Exact match, flexible extract (%) | 79.8 |
| Open Korean LLM - Ko-IFEval | 35.46 | Strict accuracy, prompt/instruction mean (%) | 72.9 |
| Open Korean LLM Leaderboard | 38.74 | Average Score (%) | 68.4 |
| Open Ko-LLM Leaderboard | 38.74 | Average (%) | 68.3 |
| Open Korean LLM - KorNAT-Helpful | 48.45 | Normalized accuracy (%) | 68.1 |
| Open Korean LLM - Ko-EQ-Bench | 15.84 | EQ-Bench score | 61.2 |
| Open Korean LLM - Ko-Winogrande | 59.19 | Accuracy (%) | 44.4 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.73 | Normalized accuracy (%) | 40.9 |
| Open Korean LLM - KorNAT-Harmless | 61.77 | Normalized accuracy (%) | 33.7 |
| Open Korean LLM - KorNAT-CKA | 19.92 | Normalized accuracy (%) | 27.3 |
Interactive version: theaggregate.ai/model?slug=naps-llama-3-1-instruct-v0-5-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.