Yi-6B-Llama: benchmark results
Provider: 01.AI. Access: Open.
Unified ELO 1303 ± 17, rank #2448 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 23.74 | Normalized accuracy (%) | 55.6 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Harmless | 60.64 | Normalized accuracy (%) | 16.7 |
| Open Korean LLM - KorNAT-Helpful | 42.12 | Normalized accuracy (%) | 14.8 |
| Open Korean LLM - Ko-IFEval | 18.85 | Strict accuracy, prompt/instruction mean (%) | 14.5 |
| Open Korean LLM - Ko-Winogrande | 52.09 | Accuracy (%) | 8.3 |
| Open Korean LLM Leaderboard | 28.68 | Average Score (%) | 7.6 |
| Open Ko-LLM Leaderboard | 28.68 | Average (%) | 7.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0 | Exact match, flexible extract (%) | 2 |
| Open Korean LLM - KorNAT-CKA | 9.74 | Normalized accuracy (%) | 1.7 |
Interactive version: theaggregate.ai/model?slug=yi-6b-llama · How It Works · Data refreshed daily, snapshot 2026-09-19.