solar-ko-recovery-11B-chat: benchmark results
Provider: Upstage. Access: Open.
Unified ELO 1451 ± 17, rank #1519 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 69.46 | Accuracy (%) | 94.9 |
| Open Korean LLM - KorNAT-CKA | 33.39 | Normalized accuracy (%) | 91.8 |
| Open Korean LLM - KorNAT-Helpful | 48.15 | Normalized accuracy (%) | 65.1 |
| Open Ko-LLM Leaderboard | 37.55 | Average (%) | 62.9 |
| Open Korean LLM Leaderboard | 37.55 | Average Score (%) | 62.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.24 | Normalized accuracy (%) | 62.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 25.25 | Exact match, flexible extract (%) | 58.6 |
| Open Korean LLM - Ko-EQ-Bench | 3.1 | EQ-Bench score | 48.9 |
| Open Korean LLM - Ko-IFEval | 28.49 | Strict accuracy, prompt/instruction mean (%) | 48.1 |
| Open Korean LLM - KorNAT-Harmless | 60.21 | Normalized accuracy (%) | 12.4 |
Interactive version: theaggregate.ai/model?slug=solar-ko-recovery-11b-chat · How It Works · Data refreshed daily, snapshot 2026-09-19.