naps-solar10.7B-instruct-v0.2: benchmark results
Provider: Other. Access: Open.
Unified ELO 1477 ± 17, rank #1322 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 67.42 | Normalized accuracy (%) | 89.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 52.62 | Exact match, flexible extract (%) | 85.8 |
| Open Korean LLM - KorNAT-Helpful | 49.43 | Normalized accuracy (%) | 79.4 |
| Open Korean LLM - Ko-EQ-Bench | 29.2 | EQ-Bench score | 77.5 |
| Open Korean LLM - KorNAT-CKA | 28.11 | Normalized accuracy (%) | 74.1 |
| Open Korean LLM - Ko-Winogrande | 63.06 | Accuracy (%) | 72.1 |
| Open Korean LLM Leaderboard | 39.36 | Average Score (%) | 71.7 |
| Open Ko-LLM Leaderboard | 39.36 | Average (%) | 71.5 |
| Open Korean LLM - Ko-IFEval | 32.84 | Strict accuracy, prompt/instruction mean (%) | 64.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.21 | Normalized accuracy (%) | 24 |
Interactive version: theaggregate.ai/model?slug=naps-solar10-7b-instruct-v0-2 · How It Works · Data refreshed daily, snapshot 2026-09-19.