AGC-Bench - pron_vs_prompt: leaderboard
The "pron_vs_prompt" subtask of AGC-Bench. A task from AGC-Bench, evaluating models on open-ended creative and figurative-language generation — humor, metaphor, analogy, storytelling and brainstorming — typically graded by LLM-as-judge.
Metric: Dataset z-score. Source: huggingface.co. Saturation forecast: Estimated already saturated. 82 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K2 0905 | 1.41 | #288 |
| 2 | Kimi K2.6 | 1.19 | #104 |
| 3 | GLM-5-Turbo | 1.17 | #119 |
| 4 | Kimi K2.5 | 1.12 | #144 |
| 5 | DeepSeek V3.2 Exp | 1.07 | #234 |
| 6 | GPT-5.4 Mini | 1.06 | #212 |
| 7 | Claude Opus 4.6 | 1.04 | #63 |
| 8 | DeepSeek V3.2 | 1.03 | #205 |
| 9 | GLM-4.7 | 1.01 | #192 |
| 10 | Claude Opus 4.7 | 1 | #49 |
| 11 | GPT-5.4 Nano | 1 | #328 |
| 12 | Gemma 4 31B (IT) | 0.99 | #176 |
| 13 | GLM-5.1 | 0.99 | #97 |
| 14 | GPT-5.4 | 0.99 | #79 |
| 15 | GLM-5 | 0.97 | #141 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=agc-bench-pron-vs-prompt · How It Works · Data refreshed daily, snapshot 2026-10-20.