> ## Documentation Index > Fetch the complete documentation index at: https://docs.scaledown.ai/llms.txt > Use this file to discover all available pages before exploring further. # Overview > How ScaleDown's task-specific models compare to frontier LLMs on accuracy, cost and latency. ScaleDown models are small and built for one job each: **Classify**, **Extract**, **Summarize** and **Compress**. We benchmark each against leading general-purpose models on public datasets and compare accuracy, cost and latency side by side. The four tasks, their datasets and metrics. Accuracy and latency against GPT-5.5, Mini and Nano. ## Each comparison reports * **Accuracy**: ScaleDown versus every model in a provider's lineup. * **Cost**: price per 1K requests for each model. * **Latency**: response time per task. ## Head-to-head GPT-5.5, GPT-5.4 Mini, GPT-5.4 Nano 8.72% higher accuracy, 2.4× faster. Fable 5, Opus 4.8, Sonnet 4.6, Haiku 4.5 8.0% higher accuracy, 3.8× faster. 3.1 Pro, 3.5 Flash, 3.1 Flash-Lite 9.0% higher accuracy, 8.3× faster. Grok 4.3, Grok 4.2 7.93% higher accuracy, 2.2× faster. V4 Pro, V4 Flash 19.5% higher accuracy, 4.1× faster. Qwen3.8 Max, 27B, Qwen3.5 4B 16.71% higher accuracy, 13.9× faster. [All benchmarks](https://scaledown.ai/benchmarks): Full charts, cost tables and latency on scaledown.ai. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.