sft_merged_660: benchmark results
Provider: Other. Access: Open.
Unified ELO 1398 ± 18, rank #1922 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 30.28 | Normalized accuracy (%) | 82.6 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.75 | Normalized accuracy (%) | 69.5 |
| Open Korean LLM - Ko-IFEval | 30.56 | Strict accuracy, prompt/instruction mean (%) | 56.7 |
| Open Korean LLM - Ko-Winogrande | 58.88 | Accuracy (%) | 42.2 |
| Open Korean LLM Leaderboard | 33.46 | Average Score (%) | 42 |
| Open Ko-LLM Leaderboard | 33.46 | Average (%) | 41.8 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Harmless | 61.11 | Normalized accuracy (%) | 23.2 |
| Open Korean LLM - KorNAT-Helpful | 43 | Normalized accuracy (%) | 20.7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 2.2 | Exact match, flexible extract (%) | 18.3 |
Interactive version: theaggregate.ai/model?slug=sft-merged-660 · How It Works · Data refreshed daily, snapshot 2026-09-19.