Yi-1.5-9B-Chat-16K-abliterated: benchmark results
byroneverson's abliterated (refusal-removed) version of 01.AI's Yi-1.5 9B Chat 16K. Provider: byroneverson. Released 2024-09-03. Access: Open.
Aggregate Rating 1428 ± 18, rank #1106 of 1656 rated models, from 29 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 47.34 | Score | 92.6 |
| Open Korean LLM - Ko-EQ-Bench | 36.3 | EQ-Bench score | 86.5 |
| Open Korean LLM - Ko-IFEval | 41.06 | Strict accuracy, prompt/instruction mean (%) | 83.9 |
| Open Chinese LLM - GSM8K | 58.68 | Accuracy (%) | 81.7 |
| Open Chinese LLM - ARC Challenge | 58.11 | Accuracy (%) | 78.8 |
| Open Chinese LLM - C-Eval Semantic | 85.54 | Accuracy (%) | 77.2 |
| Open Chinese LLM Leaderboard | 63.48 | Official Nonzero-Task Mean (%) | 76.9 |
| Open Chinese LLM - HellaSwag | 64.48 | Accuracy (%) | 76.3 |
| Open Chinese LLM - CMMLU | 62.03 | Accuracy (%) | 71.9 |
| Open LLM Leaderboard - GPQA | 31.29 | Score | 70 |
| Open LLM Leaderboard - IFEval | 55.28 | Score | 66.8 |
| Open LLM Leaderboard - MMLU-Pro | 38.23 | Score | 66.7 |
Interactive version: theaggregate.ai/model?slug=yi-1-5-9b-chat-16k-abliterated · How It Works · Data refreshed daily, snapshot 2026-10-20.