M-SOLAR-10.7B-v1.3: benchmark results
Provider: Other. Access: Open.
Unified ELO 1460 ± 17, rank #1450 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 30.23 | Normalized accuracy (%) | 82.5 |
| Open Korean LLM - Ko-Winogrande | 64.4 | Accuracy (%) | 78.4 |
| Open Korean LLM - Ko-EQ-Bench | 29.12 | EQ-Bench score | 77.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 40.86 | Exact match, flexible extract (%) | 75.3 |
| Open Ko-LLM Leaderboard | 37.67 | Average (%) | 63.4 |
| Open Korean LLM Leaderboard | 37.67 | Average Score (%) | 63.4 |
| Open Korean LLM - KorNAT-Helpful | 47.1 | Normalized accuracy (%) | 53.1 |
| Open Korean LLM - KorNAT-Harmless | 62.97 | Normalized accuracy (%) | 52.6 |
| Open Korean LLM - Ko-IFEval | 28.82 | Strict accuracy, prompt/instruction mean (%) | 49.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.73 | Normalized accuracy (%) | 40.9 |
Interactive version: theaggregate.ai/model?slug=m-solar-10-7b-v1-3 · How It Works · Data refreshed daily, snapshot 2026-09-19.