ktdsbaseLM-v0.13-onbased-llama3.1: benchmark results
Provider: Other. Released 2024-10-06. Access: Open.
Unified ELO 1615 ± 17, rank #570 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-EQ-Bench | 61.82 | EQ-Bench score | 99.8 |
| Open Ko-LLM Leaderboard | 53.93 | Average (%) | 99.1 |
| Open Korean LLM Leaderboard | 53.93 | Average Score (%) | 99.1 |
| Open Korean LLM - KorNAT-CKA | 39.35 | Normalized accuracy (%) | 98.4 |
| Open Korean LLM - Ko-IFEval | 62.92 | Strict accuracy, prompt/instruction mean (%) | 97.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 68.61 | Exact match, flexible extract (%) | 97.2 |
| Open Korean LLM - Ko-Winogrande | 66.22 | Accuracy (%) | 87.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 25.76 | Normalized accuracy (%) | 81.3 |
| Open Korean LLM - KorNAT-Harmless | 64.41 | Normalized accuracy (%) | 74 |
| Open Korean LLM - KorNAT-Helpful | 46.95 | Normalized accuracy (%) | 50.9 |
Interactive version: theaggregate.ai/model?slug=ktdsbaselm-v0-13-onbased-llama3-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.