Synatra-11B-Testbench-2: benchmark results
Provider: Other. Access: Open.
Unified ELO 1424 ± 17, rank #1717 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 63.84 | Normalized accuracy (%) | 67.3 |
| Open Korean LLM - Ko-IFEval | 33.2 | Strict accuracy, prompt/instruction mean (%) | 65.3 |
| Open Korean LLM - KorNAT-Helpful | 47.85 | Normalized accuracy (%) | 61.8 |
| Open Korean LLM - Ko-EQ-Bench | 14.69 | EQ-Bench score | 60.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 26.46 | Exact match, flexible extract (%) | 60.3 |
| Open Korean LLM Leaderboard | 35.39 | Average Score (%) | 51.3 |
| Open Ko-LLM Leaderboard | 35.39 | Average (%) | 51.2 |
| Open Korean LLM - Ko-Winogrande | 59.27 | Accuracy (%) | 45 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.72 | Normalized accuracy (%) | 29.4 |
| Open Korean LLM - KorNAT-CKA | 16.86 | Normalized accuracy (%) | 13.5 |
Interactive version: theaggregate.ai/model?slug=synatra-11b-testbench-2 · How It Works · Data refreshed daily, snapshot 2026-09-19.