DiscoPOP-zephyr-7B-gemma: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1415 ± 52, rank #5419 of 10916 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 67.42 | Normalized accuracy (%) | 89.4 |
| Open Korean LLM - KorNAT-CKA | 31.77 | Normalized accuracy (%) | 87.6 |
| Open Korean LLM - Ko-GPQA-Diamond | 25.76 | Normalized accuracy (%) | 81.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 41.32 | Exact match, flexible extract (%) | 75.9 |
| Open Korean LLM Leaderboard | 40.21 | Average Score (%) | 75.9 |
| Open Portuguese LLM - FaQuAD NLI | 72.63 | Macro F1 (%) | 66.2 |
| Open Korean LLM - Ko-Winogrande | 61.96 | Accuracy (%) | 65.3 |
| Open Korean LLM - Ko-IFEval | 31.42 | Strict accuracy, prompt/instruction mean (%) | 59.6 |
| Open Korean LLM - Ko-EQ-Bench | 9.67 | EQ-Bench score | 55.6 |
| Open Portuguese LLM - ENEM | 57.1 | Accuracy (%) | 41.6 |
| Open Portuguese LLM - OAB Exams | 39.59 | Accuracy (%) | 41.5 |
| Open Portuguese LLM - BLUEX | 44.09 | Accuracy (%) | 35.3 |
Interactive version: theaggregate.ai/model?slug=discopop-zephyr-7b-gemma · How It Works · Data refreshed daily, snapshot 2026-11-08.