KoSOLAR-10.7B-kolon: benchmark results
Provider: Other. Access: Open.
Unified ELO 1387 ± 18, rank #2001 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 63.93 | Accuracy (%) | 76.6 |
| Open Korean LLM - KorNAT-CKA | 26.1 | Normalized accuracy (%) | 62.2 |
| Open Korean LLM - Ko-IFEval | 28.29 | Strict accuracy, prompt/instruction mean (%) | 47.2 |
| Open Korean LLM Leaderboard | 32.88 | Average Score (%) | 36.4 |
| Open Ko-LLM Leaderboard | 32.88 | Average (%) | 36.2 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.22 | Normalized accuracy (%) | 35 |
| Open Korean LLM - KorNAT-Helpful | 44.02 | Normalized accuracy (%) | 27.2 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Harmless | 60.24 | Normalized accuracy (%) | 12.7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0.15 | Exact match, flexible extract (%) | 6.3 |
Interactive version: theaggregate.ai/model?slug=kosolar-10-7b-kolon · How It Works · Data refreshed daily, snapshot 2026-09-19.