M-DIE-M-10.7B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1460 ± 18, rank #1448 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 30.58 | Normalized accuracy (%) | 84.3 |
| Open Korean LLM - Ko-EQ-Bench | 31.96 | EQ-Bench score | 81.3 |
| Open Korean LLM - Ko-Winogrande | 64.88 | Accuracy (%) | 81.2 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 38.13 | Exact match, flexible extract (%) | 72.7 |
| Open Korean LLM - KorNAT-Harmless | 63.71 | Normalized accuracy (%) | 65.8 |
| Open Ko-LLM Leaderboard | 37.57 | Average (%) | 63 |
| Open Korean LLM Leaderboard | 37.57 | Average Score (%) | 63 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.24 | Normalized accuracy (%) | 62.4 |
| Open Korean LLM - KorNAT-Helpful | 46.48 | Normalized accuracy (%) | 46.9 |
| Open Korean LLM - Ko-IFEval | 27.68 | Strict accuracy, prompt/instruction mean (%) | 44.5 |
Interactive version: theaggregate.ai/model?slug=m-die-m-10-7b · How It Works · Data refreshed daily, snapshot 2026-09-19.