AGC-Bench - chinese_homophonic_puns — leaderboard
Metric: Dataset z-score. Source: huggingface.co. 82 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 31B (IT) | 1.56 |
| 2 | Kimi K2.5 | 1.38 |
| 3 | ERNIE 4.5 300B A47B | 1.38 |
| 4 | GLM-4.5V | 1.33 |
| 5 | Claude Opus 4.7 | 1.32 |
| 6 | GLM-4.7 | 1.28 |
| 7 | Claude Opus 4.5 | 1.2 |
| 8 | DeepSeek V3.2 Exp | 1.19 |
| 9 | Claude Haiku 4.5 | 1.1 |
| 10 | DeepSeek V3.1 | 1.02 |
| 11 | Kimi K2.6 | 1.01 |
| 12 | Gemma 4 26B A4B (IT) | 0.95 |
| 13 | GPT-4.1 Mini | 0.92 |
| 14 | DeepSeek V3.1 Terminus | 0.92 |
| 15 | Claude Opus 4.6 | 0.9 |
Interactive version: theaggregate.ai/benchmark?slug=agc-bench-chinese-homophonic-puns · How the rankings work · Data refreshed daily, snapshot 2026-07-22.