M-SOLAR-10.7B-v1.2: benchmark results
Provider: Other. Access: Open.
Unified ELO 1449 ± 17, rank #1534 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 66.61 | Accuracy (%) | 88.8 |
| Open Korean LLM - Ko-EQ-Bench | 28.64 | EQ-Bench score | 76.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 35.94 | Exact match, flexible extract (%) | 69.1 |
| Open Ko-LLM Leaderboard | 37.05 | Average (%) | 60.6 |
| Open Korean LLM Leaderboard | 37.05 | Average Score (%) | 60.6 |
| Open Korean LLM - KorNAT-CKA | 25.37 | Normalized accuracy (%) | 57.3 |
| Open Korean LLM - KorNAT-Helpful | 45.92 | Normalized accuracy (%) | 40.7 |
| Open Korean LLM - KorNAT-Harmless | 61.97 | Normalized accuracy (%) | 36.4 |
| Open Korean LLM - Ko-IFEval | 23.7 | Strict accuracy, prompt/instruction mean (%) | 28.3 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.21 | Normalized accuracy (%) | 24 |
Interactive version: theaggregate.ai/model?slug=m-solar-10-7b-v1-2 · How It Works · Data refreshed daily, snapshot 2026-09-19.