leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT: benchmark results
Provider: Other. Access: Open.
Unified ELO 1442 ± 17, rank #1575 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 64.72 | Accuracy (%) | 80.3 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.24 | Normalized accuracy (%) | 62.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 27.22 | Exact match, flexible extract (%) | 61.3 |
| Open Korean LLM - Ko-EQ-Bench | 14.53 | EQ-Bench score | 60.2 |
| Open Ko-LLM Leaderboard | 36.83 | Average (%) | 59.3 |
| Open Korean LLM Leaderboard | 36.83 | Average Score (%) | 59.3 |
| Open Korean LLM - Ko-IFEval | 30.92 | Strict accuracy, prompt/instruction mean (%) | 58.6 |
| Open Korean LLM - KorNAT-CKA | 23.93 | Normalized accuracy (%) | 48.7 |
| Open Korean LLM - KorNAT-Harmless | 61.91 | Normalized accuracy (%) | 35.7 |
| Open Korean LLM - KorNAT-Helpful | 42.8 | Normalized accuracy (%) | 18.8 |
Interactive version: theaggregate.ai/model?slug=leaderboard-inst-v1-3-open-hermes-ldcc-solar-10-7b-sft · How It Works · Data refreshed daily, snapshot 2026-09-19.