SOLAR-10.7B-orca-alpaca-gpt4-lora-653: benchmark results
Provider: Upstage. Access: Open.
Unified ELO 1470 ± 17, rank #1380 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 65.67 | Accuracy (%) | 85.7 |
| Open Korean LLM - KorNAT-Helpful | 49.93 | Normalized accuracy (%) | 82.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 40.33 | Exact match, flexible extract (%) | 74.9 |
| Open Korean LLM - KorNAT-CKA | 27.88 | Normalized accuracy (%) | 72.3 |
| Open Korean LLM Leaderboard | 39.38 | Average Score (%) | 72 |
| Open Ko-LLM Leaderboard | 39.38 | Average (%) | 71.7 |
| Open Korean LLM - Ko-IFEval | 34.48 | Strict accuracy, prompt/instruction mean (%) | 71 |
| Open Korean LLM - KorNAT-Harmless | 63.25 | Normalized accuracy (%) | 59 |
| Open Korean LLM - Ko-EQ-Bench | 9.01 | EQ-Bench score | 55.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.22 | Normalized accuracy (%) | 35 |
Interactive version: theaggregate.ai/model?slug=solar-10-7b-orca-alpaca-gpt4-lora-653 · How It Works · Data refreshed daily, snapshot 2026-09-19.