YOMI-Bench - Rhyme Selection (Kanji): leaderboard
Choose, among four options, the word whose vowel sequence matches a given word written in kanji, which requires knowing its reading; from YOMI-Bench (2026). Accuracy in percent averaged over five paraphrased prompts; higher is better.
Metric: Accuracy (%; four-option choice of the word sharing the vowel sequence of a word written in kanji; 120 items; mean over five paraphrased prompts; accuracy as a fraction x100). Source: arxiv.org. Saturation forecast: Estimated already saturated. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 100 | #167 |
| 2 | Claude Sonnet 4.5 | 95.59 | #250 |
| 3 | Gemini 2.5 Flash | 93.8 | #453 |
| 4 | GPT-4o | 58.2 | #741 |
| 5 | Mistral Medium 3.1 | 34.6 | #852 |
| 6 | Ministral-8B-Instruct-2410 | 29.6 | #4684 |
| 7 | Llama-3.1-Swallow-8B-Instruct-v0.5 | 29.6 | #2704 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=yomi-bench-rhyme-selection-kanji · How It Works · Data refreshed daily, snapshot 2026-11-13.