MK_Nemo_12B: benchmark results
Provider: Other. Released 2024-11-06. Access: Open.
Unified ELO 1589 ± 17, rank #674 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-EQ-Bench | 59.1 | EQ-Bench score | 98.4 |
| Open Ko-LLM Leaderboard | 51.55 | Average (%) | 97.9 |
| Open Korean LLM Leaderboard | 51.55 | Average Score (%) | 97.9 |
| Open Korean LLM - Ko-Winogrande | 71.9 | Accuracy (%) | 97.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 63.38 | Exact match, flexible extract (%) | 96 |
| Open Korean LLM - Ko-IFEval | 53.03 | Strict accuracy, prompt/instruction mean (%) | 95.6 |
| Open Korean LLM - KorNAT-CKA | 29.86 | Normalized accuracy (%) | 81.5 |
| Open Korean LLM - KorNAT-Helpful | 49.35 | Normalized accuracy (%) | 78.6 |
| Open Korean LLM - KorNAT-Harmless | 64.2 | Normalized accuracy (%) | 71.6 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.24 | Normalized accuracy (%) | 62.4 |
Interactive version: theaggregate.ai/model?slug=mk-nemo-12b · How It Works · Data refreshed daily, snapshot 2026-09-19.