AGC-Bench - meta4xnli: leaderboard
The "meta4xnli" 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: Around February 2027. 83 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 0.96 | #142 |
| 2 | Kimi K2.5 | 0.96 | #144 |
| 3 | Claude Opus 4.6 | 0.87 | #63 |
| 4 | Claude Opus 4.7 | 0.87 | #49 |
| 5 | Claude Opus 4.5 | 0.87 | #83 |
| 6 | Claude Sonnet 4.6 | 0.87 | #90 |
| 7 | GLM-5 | 0.86 | #141 |
| 8 | GLM-5-Turbo | 0.86 | #119 |
| 9 | Kimi K2 0905 | 0.79 | #288 |
| 10 | Hermes-3-Llama-3.1-405B | 0.78 | #510 |
| 11 | Qwen 3.5 Flash (02-23) | 0.78 | #185 |
| 12 | Claude Sonnet 4 | 0.78 | #199 |
| 13 | DeepSeek V3.2 Exp | 0.71 | #234 |
| 14 | GPT-5.1 | 0.71 | #135 |
| 15 | GPT-5.5 | 0.7 | #31 |
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-meta4xnli · How It Works · Data refreshed daily, snapshot 2026-10-20.