KoSOLAR-10.7B-qlora-v1.2.1: benchmark results
Provider: Other. Access: Open.
Unified ELO 1279 ± 18, rank #2522 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 26.26 | Normalized accuracy (%) | 85.5 |
| Open Korean LLM - KorNAT-Harmless | 66.3 | Normalized accuracy (%) | 85.3 |
| Open Korean LLM - KorNAT-CKA | 25.83 | Normalized accuracy (%) | 61 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 19.56 | Strict accuracy, prompt/instruction mean (%) | 16.3 |
| Open Korean LLM Leaderboard | 27.77 | Average Score (%) | 2.9 |
| Open Ko-LLM Leaderboard | 27.77 | Average (%) | 2.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0 | Exact match, flexible extract (%) | 2 |
| Open Korean LLM - Ko-Winogrande | 48.7 | Accuracy (%) | 0.9 |
| Open Korean LLM - KorNAT-Helpful | 33.9 | Normalized accuracy (%) | 0.4 |
Interactive version: theaggregate.ai/model?slug=kosolar-10-7b-qlora-v1-2-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.