AGC-Bench - poetmt — leaderboard
Metric: Dataset z-score. Source: huggingface.co. 82 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 1.55 |
| 2 | Claude Opus 4.7 | 1.52 |
| 3 | GPT-5.5 | 1.42 |
| 4 | GPT-5.4 | 1.41 |
| 5 | Claude Opus 4.5 | 1.32 |
| 6 | DeepSeek V3.2 Exp | 1.26 |
| 7 | Kimi K2 0905 | 1.2 |
| 8 | Claude Sonnet 4.5 | 1.2 |
| 9 | DeepSeek V3.2 | 1.17 |
| 10 | DeepSeek V3 (0324) | 1.12 |
| 11 | GLM-5-Turbo | 1.07 |
| 12 | GLM-5.1 | 1.06 |
| 13 | GLM-5 | 1.04 |
| 14 | GPT-5.1 | 1.04 |
| 15 | DeepSeek V3.1 Terminus | 0.91 |
Interactive version: theaggregate.ai/benchmark?slug=agc-bench-poetmt · How the rankings work · Data refreshed daily, snapshot 2026-07-22.