AGC-Bench - slang_generation — leaderboard
Metric: Dataset z-score. Source: huggingface.co. 83 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 1.52 |
| 2 | DeepSeek V3.2 | 1.26 |
| 3 | Claude Opus 4.5 | 1.24 |
| 4 | GLM-5 | 1.21 |
| 5 | Claude Sonnet 4 | 1.14 |
| 6 | Claude Opus 4.6 | 1.13 |
| 7 | Llama 3.2 11B Instruct | 1.1 |
| 8 | Gemma 4 31B (IT) | 1.03 |
| 9 | Gemini 2.5 Flash | 1.03 |
| 10 | GLM-5-Turbo | 1 |
| 11 | Gemma 4 26B A4B (IT) | 0.99 |
| 12 | DeepSeek V3.1 | 0.97 |
| 13 | DeepSeek V3.2 Exp | 0.91 |
| 14 | GPT-5.4 Mini | 0.81 |
| 15 | Claude 3.7 Sonnet | 0.73 |
Interactive version: theaggregate.ai/benchmark?slug=agc-bench-slang-generation · How the rankings work · Data refreshed daily, snapshot 2026-07-22.