SOLAR-10.7B-ko_alpaca: benchmark results
Provider: Upstage. Access: Open.
Unified ELO 1464 ± 17, rank #1419 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-EQ-Bench | 31.55 | EQ-Bench score | 80.9 |
| Open Korean LLM - KorNAT-Harmless | 64.55 | Normalized accuracy (%) | 74.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 39.27 | Exact match, flexible extract (%) | 73.6 |
| Open Korean LLM Leaderboard | 38.55 | Average Score (%) | 67.9 |
| Open Ko-LLM Leaderboard | 38.55 | Average (%) | 67.8 |
| Open Korean LLM - Ko-Winogrande | 62.19 | Accuracy (%) | 67.2 |
| Open Korean LLM - KorNAT-Helpful | 48.1 | Normalized accuracy (%) | 64.6 |
| Open Korean LLM - Ko-IFEval | 30.48 | Strict accuracy, prompt/instruction mean (%) | 56.4 |
| Open Korean LLM - KorNAT-CKA | 22.77 | Normalized accuracy (%) | 41.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.73 | Normalized accuracy (%) | 40.9 |
Interactive version: theaggregate.ai/model?slug=solar-10-7b-ko-alpaca · How It Works · Data refreshed daily, snapshot 2026-09-19.