all-you-need-is: benchmark results
Provider: Other. Access: Open.
Unified ELO 1485 ± 17, rank #1226 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 68.88 | Normalized accuracy (%) | 92.6 |
| Open Korean LLM - Ko-Winogrande | 67.64 | Accuracy (%) | 91.6 |
| Open Korean LLM - KorNAT-Helpful | 50.15 | Normalized accuracy (%) | 84.2 |
| Open Korean LLM - Ko-EQ-Bench | 33 | EQ-Bench score | 82.6 |
| Open Korean LLM Leaderboard | 40.47 | Average Score (%) | 77.2 |
| Open Ko-LLM Leaderboard | 40.47 | Average (%) | 77.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 36.01 | Exact match, flexible extract (%) | 69.2 |
| Open Korean LLM - Ko-IFEval | 28.05 | Strict accuracy, prompt/instruction mean (%) | 46.1 |
| Open Korean LLM - KorNAT-CKA | 20.79 | Normalized accuracy (%) | 31.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.71 | Normalized accuracy (%) | 18.8 |
Interactive version: theaggregate.ai/model?slug=all-you-need-is · How It Works · Data refreshed daily, snapshot 2026-09-19.