byt5-xxl: benchmark results
Provider: Other. Access: Open.
Unified ELO 1344 ± 18, rank #2266 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 27.27 | Normalized accuracy (%) | 92.4 |
| Open Korean LLM - Ko-IFEval | 27.3 | Strict accuracy, prompt/instruction mean (%) | 42.4 |
| Open Korean LLM - KorNAT-Helpful | 45.02 | Normalized accuracy (%) | 33.9 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM Leaderboard | 30.6 | Average Score (%) | 20.3 |
| Open Ko-LLM Leaderboard | 30.6 | Average (%) | 20.1 |
| Open Korean LLM - Ko-Winogrande | 54.3 | Accuracy (%) | 15.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0.76 | Exact match, flexible extract (%) | 10.3 |
| Open Korean LLM - KorNAT-CKA | 13.76 | Normalized accuracy (%) | 4.9 |
| Open Korean LLM - KorNAT-Harmless | 57.22 | Normalized accuracy (%) | 1.7 |
Interactive version: theaggregate.ai/model?slug=byt5-xxl · How It Works · Data refreshed daily, snapshot 2026-09-19.