Synatra-10.7B-v0.4: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1426 ± 27, rank #4888 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 69.06 | Accuracy (%) | 94.3 |
| Open Korean LLM - Ko-IFEval | 42.58 | Strict accuracy, prompt/instruction mean (%) | 86.3 |
| Open Korean LLM Leaderboard | 41.9 | Average Score (%) | 83.9 |
| Open LLM Leaderboard v1 - WinoGrande | 81.85 | Accuracy (%) (5-shot) | 81.1 |
| Open Korean LLM - KorNAT-Helpful | 48.88 | Normalized accuracy (%) | 74.1 |
| Open Korean LLM - KorNAT-Harmless | 64.03 | Normalized accuracy (%) | 69.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 36.01 | Exact match, flexible extract (%) | 69.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 64.93 | Normalized accuracy (%) (25-shot) | 68.5 |
| Open Korean LLM - Ko-EQ-Bench | 21.77 | EQ-Bench score | 67.1 |
| Open Korean LLM - KorNAT-CKA | 26.48 | Normalized accuracy (%) | 64.9 |
| Open LLM Leaderboard v1 - GSM8K | 50.04 | Accuracy (%) (5-shot) | 62.5 |
| Open LLM Leaderboard v1 - MMLU | 62.5 | Accuracy (%) (5-shot) | 55.5 |
Interactive version: theaggregate.ai/model?slug=synatra-10-7b-v0-4 · How It Works · Data refreshed daily, snapshot 2026-11-08.