DITING - Idiom Translation: leaderboard
DITING subtask measuring accurate translation of Chinese idioms (chengyu) into natural English equivalents.
Metric: Score. Source: huggingface.co. Saturation forecast: Estimated already saturated. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Seed-X-PPO-7B | 5.42 | #575 |
| 2 | DeepSeek V3 | 5.14 | #321 |
| 3 | GPT-4o | 5.04 | #343 |
| 4 | Qwen 3 32B | 4.5 | #443 |
| 5 | Qwen 3 14B | 4.24 | #537 |
| 6 | Qwen 3 8B | 4.1 | #674 |
| 7 | Llama 3 70B | 2.76 | #631 |
| 8 | Llama 3 8B | 2.64 | #1242 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=diting-idiom-translation · How It Works · Data refreshed daily, snapshot 2026-10-20.