Synatra-V0.1-7B-Instruct: benchmark results
Provider: maywell. Access: Open.
Aggregate Rating 1350 ± 26, rank #7692 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 64.96 | Normalized accuracy (%) | 78.3 |
| Open Korean LLM - Ko-EQ-Bench | 21.2 | EQ-Bench score | 66.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 55.76 | MC2 (%) (0-shot) | 66 |
| Open Korean LLM - KorNAT-Helpful | 48.18 | Normalized accuracy (%) | 65.3 |
| Open Korean LLM - Ko-IFEval | 32.91 | Strict accuracy, prompt/instruction mean (%) | 64.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 29.11 | Exact match, flexible extract (%) | 63.4 |
| Open Korean LLM Leaderboard | 37.58 | Average Score (%) | 62.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.74 | Normalized accuracy (%) | 55.6 |
| Open LLM Leaderboard v1 - GSM8K | 19.41 | Accuracy (%) (5-shot) | 40.6 |
| Open LLM Leaderboard v1 - MMLU | 55.29 | Accuracy (%) (5-shot) | 35.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 55.29 | Normalized accuracy (%) (25-shot) | 33.1 |
| Open Korean LLM - Ko-Winogrande | 57.38 | Accuracy (%) | 31.3 |
Interactive version: theaggregate.ai/model?slug=synatra-v0-1-7b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.