llamion-14B-chat: benchmark results
Provider: Other.
Aggregate Rating 1401 ± 30, rank #6054 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 28.28 | Normalized accuracy (%) | 96.6 |
| Open Korean LLM - KorNAT-CKA | 31.56 | Normalized accuracy (%) | 87 |
| Open Korean LLM Leaderboard | 41.19 | Average Score (%) | 81.6 |
| Open Korean LLM - Ko-EQ-Bench | 31.5 | EQ-Bench score | 80.7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 37.6 | Exact match, flexible extract (%) | 71.7 |
| Open Korean LLM - Ko-Winogrande | 61.56 | Accuracy (%) | 63 |
| Open LLM Leaderboard v1 - MMLU | 63.28 | Accuracy (%) (5-shot) | 59.6 |
| Open Korean LLM - KorNAT-Harmless | 63.09 | Normalized accuracy (%) | 55.4 |
| Open LLM Leaderboard v1 - GSM8K | 36.69 | Accuracy (%) (5-shot) | 52 |
| Open Korean LLM - KorNAT-Helpful | 46.05 | Normalized accuracy (%) | 41.8 |
| Open Korean LLM - Ko-IFEval | 26.52 | Strict accuracy, prompt/instruction mean (%) | 39.1 |
| Open LLM Leaderboard v1 - HellaSwag | 78.99 | Normalized accuracy (%) (10-shot) | 36.4 |
Interactive version: theaggregate.ai/model?slug=llamion-14b-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.