M-SOLAR-10.7B-v1.0: benchmark results
Provider: Other. Access: Open.
Unified ELO 1471 ± 17, rank #1369 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 66.93 | Accuracy (%) | 90.1 |
| Open Korean LLM - Ko-EQ-Bench | 28.29 | EQ-Bench score | 75.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 41.09 | Exact match, flexible extract (%) | 75.6 |
| Open Korean LLM - KorNAT-CKA | 28.31 | Normalized accuracy (%) | 75 |
| Open Korean LLM - KorNAT-Helpful | 48.65 | Normalized accuracy (%) | 71 |
| Open Ko-LLM Leaderboard | 39 | Average (%) | 69.4 |
| Open Korean LLM Leaderboard | 39 | Average Score (%) | 69.4 |
| Open Korean LLM - Ko-IFEval | 33.53 | Strict accuracy, prompt/instruction mean (%) | 67.5 |
| Open Korean LLM - KorNAT-Harmless | 63.66 | Normalized accuracy (%) | 65.3 |
| Open Korean LLM - Ko-GPQA-Diamond | 18.69 | Normalized accuracy (%) | 4.1 |
Interactive version: theaggregate.ai/model?slug=m-solar-10-7b-v1-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.