YOMI-Bench - Kanji Reading Prediction (Single Reading): leaderboard
Generate the reading of a Japanese word written in kanji, for kanji with only one reading, from YOMI-Bench (2026). Exact-match accuracy in percent averaged over five paraphrased prompts; higher is better.
Metric: Accuracy (%; exact match of the generated reading of a word, extracted by regular expression; 120 items on kanji with a single reading; 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 | Claude Sonnet 4.5 | 99.6 | #250 |
| 2 | GPT-5 | 98.4 | #167 |
| 3 | Gemini 2.5 Flash | 98.2 | #453 |
| 4 | GPT-4o | 96.2 | #741 |
| 5 | Llama-3.1-Swallow-8B-Instruct-v0.5 | 82.19 | #2704 |
| 6 | Mistral Medium 3.1 | 80.19 | #852 |
| 7 | Ministral-8B-Instruct-2410 | 46.79 | #4684 |
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-kanji-reading-prediction-single-reading · How It Works · Data refreshed daily, snapshot 2026-11-13.