KoSoLAR-10.7B-v0.2.1.4_dedup_1: benchmark results
Provider: Other. Access: Open.
Unified ELO 1423 ± 17, rank #1724 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 28.53 | Normalized accuracy (%) | 76.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 25.25 | Normalized accuracy (%) | 75.9 |
| Open Korean LLM - Ko-Winogrande | 63.46 | Accuracy (%) | 74.2 |
| Open Korean LLM - Ko-EQ-Bench | 16.57 | EQ-Bench score | 61.9 |
| Open Korean LLM Leaderboard | 35.12 | Average Score (%) | 49.9 |
| Open Ko-LLM Leaderboard | 35.12 | Average (%) | 49.8 |
| Open Korean LLM - KorNAT-Helpful | 44.92 | Normalized accuracy (%) | 33.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 9.1 | Exact match, flexible extract (%) | 32.2 |
| Open Korean LLM - Ko-IFEval | 24.94 | Strict accuracy, prompt/instruction mean (%) | 31.6 |
| Open Korean LLM - KorNAT-Harmless | 61.4 | Normalized accuracy (%) | 28 |
Interactive version: theaggregate.ai/model?slug=kosolar-10-7b-v0-2-1-4-dedup-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.