solar-ko-1.3-mss: benchmark results
Provider: Upstage. Access: Open.
Unified ELO 1419 ± 17, rank #1756 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 65.19 | Accuracy (%) | 83.3 |
| Open Korean LLM - KorNAT-CKA | 28.4 | Normalized accuracy (%) | 75.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 29.87 | Exact match, flexible extract (%) | 64.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.24 | Normalized accuracy (%) | 62.4 |
| Open Korean LLM - KorNAT-Harmless | 62.62 | Normalized accuracy (%) | 47.4 |
| Open Korean LLM Leaderboard | 34.19 | Average Score (%) | 46.7 |
| Open Ko-LLM Leaderboard | 34.19 | Average (%) | 46.6 |
| Open Korean LLM - KorNAT-Helpful | 46.23 | Normalized accuracy (%) | 43.3 |
| Open Korean LLM - Ko-IFEval | 25.91 | Strict accuracy, prompt/instruction mean (%) | 37.2 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
Interactive version: theaggregate.ai/model?slug=solar-ko-1-3-mss · How It Works · Data refreshed daily, snapshot 2026-09-19.