naps-llama-3.1_instruct-v0.6.0: benchmark results
Provider: NAPS-ai. Released 2024-10-01. Access: Open.
Aggregate Rating 1405 ± 39, rank #5828 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 26.26 | Normalized accuracy (%) | 85.5 |
| Open Korean LLM - Ko-IFEval | 35.77 | Strict accuracy, prompt/instruction mean (%) | 73.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 38.89 | Exact match, flexible extract (%) | 73.3 |
| Open Korean LLM Leaderboard | 39.37 | Average Score (%) | 71.9 |
| Open Korean LLM - Ko-Winogrande | 61.8 | Accuracy (%) | 64.2 |
| Open Korean LLM - Ko-EQ-Bench | 15.83 | EQ-Bench score | 61.1 |
| Open Korean LLM - KorNAT-Harmless | 63.28 | Normalized accuracy (%) | 59.5 |
| Open Korean LLM - KorNAT-CKA | 23.92 | Normalized accuracy (%) | 48.5 |
| Open LLM Leaderboard - MMLU-Pro | 32.41 | Score | 44.6 |
| Open LLM Leaderboard - GPQA | 28.19 | Score | 36.8 |
| Open LLM Leaderboard - MATH Level 5 | 6.42 | Score | 34.9 |
| Open LLM Leaderboard - BBH | 45.28 | Score | 34.8 |
Interactive version: theaggregate.ai/model?slug=naps-llama-3-1-instruct-v0-6-0 · How It Works · Data refreshed daily, snapshot 2026-11-08.