sft-solar-10.7B-v1.1: benchmark results
Provider: Other. Access: Open.
Unified ELO 1374 ± 18, rank #2096 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 28.51 | Normalized accuracy (%) | 76.1 |
| Open Korean LLM - Ko-Winogrande | 61.88 | Accuracy (%) | 64.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 26.91 | Exact match, flexible extract (%) | 60.8 |
| Open Korean LLM - Ko-IFEval | 30.43 | Strict accuracy, prompt/instruction mean (%) | 56.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.22 | Normalized accuracy (%) | 35 |
| Open Korean LLM - KorNAT-Harmless | 61.62 | Normalized accuracy (%) | 31.8 |
| Open Korean LLM - KorNAT-Helpful | 44.6 | Normalized accuracy (%) | 31.2 |
| Open Korean LLM Leaderboard | 31.11 | Average Score (%) | 25.1 |
| Open Ko-LLM Leaderboard | 31.11 | Average (%) | 25 |
| Open Korean LLM - Ko-EQ-Bench | -16.88 | EQ-Bench score | 1.3 |
Interactive version: theaggregate.ai/model?slug=sft-solar-10-7b-v1-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.