Sakura-SOLAR-Instruct: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1460 ± 28, rank #3349 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 71.79 | MC2 (%) (0-shot) | 92.2 |
| Open LLM Leaderboard v1 - HellaSwag | 88.42 | Normalized accuracy (%) (10-shot) | 91.7 |
| Open Korean LLM - KorNAT-Harmless | 67.77 | Normalized accuracy (%) | 90.5 |
| Open LLM Leaderboard v1 - WinoGrande | 83.66 | Accuracy (%) (5-shot) | 90.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 70.99 | Normalized accuracy (%) (25-shot) | 87.5 |
| Open LLM Leaderboard v1 - MMLU | 66.33 | Accuracy (%) (5-shot) | 86.8 |
| Open Korean LLM - Ko-EQ-Bench | 34.84 | EQ-Bench score | 84.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 50.8 | Exact match, flexible extract (%) | 84.3 |
| Open Korean LLM - KorNAT-Helpful | 49.63 | Normalized accuracy (%) | 80.3 |
| Open LLM Leaderboard v1 - GSM8K | 65.2 | Accuracy (%) (5-shot) | 79.5 |
| Open Korean LLM Leaderboard | 40.09 | Average Score (%) | 75.6 |
| Open Korean LLM - Ko-Winogrande | 62.75 | Accuracy (%) | 70.4 |
Interactive version: theaggregate.ai/model?slug=sakura-solar-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.