lsh-finetune-v0.11: benchmark results
Provider: Other. Access: Open.
Unified ELO 1365 ± 17, rank #2143 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 48.4 | Normalized accuracy (%) | 67.6 |
| Open Korean LLM - KorNAT-Harmless | 62.86 | Normalized accuracy (%) | 51 |
| Open Korean LLM - Ko-IFEval | 28.82 | Strict accuracy, prompt/instruction mean (%) | 49.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 17.06 | Exact match, flexible extract (%) | 47.8 |
| Open Korean LLM - Ko-Winogrande | 57.06 | Accuracy (%) | 29.3 |
| Open Korean LLM Leaderboard | 31.14 | Average Score (%) | 25.5 |
| Open Ko-LLM Leaderboard | 31.14 | Average (%) | 25.3 |
| Open Korean LLM - KorNAT-CKA | 15.95 | Normalized accuracy (%) | 11.2 |
| Open Korean LLM - Ko-EQ-Bench | -1.12 | EQ-Bench score | 4 |
| Open Korean LLM - Ko-GPQA-Diamond | 17.17 | Normalized accuracy (%) | 0.9 |
Interactive version: theaggregate.ai/model?slug=lsh-finetune-v0-11 · How It Works · Data refreshed daily, snapshot 2026-09-19.