MultiLexNorm++ (LLM Pipeline) - Korean: leaderboard
Metric: Error reduction rate (%; (correct minus wrong normalizations) / words that need normalization, so 0 equals leaving the text unchanged and a negative score means more wrong than right edits; the floor is -100 divided by the share of words needing normalization; 8-shot prompting, mean of three runs; the LLM normalizes the words an XLM-R detector flags after a training-lexicon lookup; the new Korean social-media set, 7.52% of words normalized). Source: arxiv.org. Saturation forecast: Estimated already saturated. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 72B Instruct | -6.88 |
| 2 | Gemma 3 27B (IT) | -8.73 |
| 3 | GPT-4o | -8.73 |
| 4 | Llama 3.3 70B Instruct | -14.82 |
Interactive version: theaggregate.ai/benchmark?slug=multilexnorm-plus-plus-llm-pipeline-korean · How It Works · Data refreshed daily, snapshot 2026-09-26.