QUIET: leaderboard
Large language models (LLMs) face a dual challenge in creative capability evaluation: existing benchmarks (e.g., Story Cloze Test, HellaSwag) measure models' discriminative ability over narrative continuation using multiple-choice recognition paradigms, rather than directly measuring creative generation capability; rubric-based scoring and LLM-as-Judge methods rely on subjective dimension assessme
Metric: QUIET Total (self-reported). Source: benchmarklist.com. Saturation forecast: Around June 2027. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 8.69 | #58 |
| 2 | Gemini 2.5 Pro | 8.44 | #152 |
| 3 | GLM-5.1 (Thinking) | 8.4 | #97 (GLM-5.1) |
| 4 | Claude Opus 4.6 | 8.38 | #63 |
| 5 | Qwen 3.6 Plus (Thinking) | 8.18 | #120 (Qwen 3.6 Plus) |
| 6 | Grok 4.1 Fast | 8.11 | #217 |
| 7 | GPT-5.4 Mini | 8.03 | #212 |
| 8 | Qwen Max | 7.62 | #382 |
| 9 | GPT-3.5 Turbo | 6.44 | #865 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=quiet · How It Works · Data refreshed daily, snapshot 2026-10-20.