KoSOLAR-10.7B-v0.3: benchmark results
Provider: Other.
Aggregate Rating 1407 ± 31, rank #5766 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 66.85 | Accuracy (%) | 89.8 |
| Open LLM Leaderboard v1 - WinoGrande | 82.48 | Accuracy (%) (5-shot) | 84.3 |
| Open LLM Leaderboard v1 - MMLU | 64.51 | Accuracy (%) (5-shot) | 71.8 |
| Open Korean LLM - KorNAT-CKA | 27.8 | Normalized accuracy (%) | 71.7 |
| Open LLM Leaderboard v1 - GSM8K | 50.49 | Accuracy (%) (5-shot) | 62.8 |
| Open LLM Leaderboard v1 - HellaSwag | 83.73 | Normalized accuracy (%) (10-shot) | 61 |
| Open Korean LLM - KorNAT-Helpful | 47.75 | Normalized accuracy (%) | 60 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.8 | Normalized accuracy (%) (25-shot) | 59.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.74 | Normalized accuracy (%) | 55.6 |
| Open Korean LLM - KorNAT-Harmless | 62.65 | Normalized accuracy (%) | 48.1 |
| Open Korean LLM Leaderboard | 33.82 | Average Score (%) | 44.5 |
| Open Korean LLM - Ko-IFEval | 23.73 | Strict accuracy, prompt/instruction mean (%) | 28.4 |
Interactive version: theaggregate.ai/model?slug=kosolar-10-7b-v0-3 · How It Works · Data refreshed daily, snapshot 2026-11-08.