cdlm-7-ko-nl2sql-v1.0: benchmark results
Provider: Other. Access: Open.
Unified ELO 1367 ± 17, rank #2128 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 47.83 | Normalized accuracy (%) | 61.4 |
| Open Korean LLM - Ko-IFEval | 29.58 | Strict accuracy, prompt/instruction mean (%) | 52.2 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 8.79 | Exact match, flexible extract (%) | 31.6 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.72 | Normalized accuracy (%) | 29.4 |
| Open Korean LLM Leaderboard | 31.37 | Average Score (%) | 27.2 |
| Open Ko-LLM Leaderboard | 31.37 | Average (%) | 27 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Harmless | 61.16 | Normalized accuracy (%) | 24.1 |
| Open Korean LLM - Ko-Winogrande | 53.99 | Accuracy (%) | 14.9 |
| Open Korean LLM - KorNAT-CKA | 16.38 | Normalized accuracy (%) | 12.1 |
Interactive version: theaggregate.ai/model?slug=cdlm-7-ko-nl2sql-v1-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.