Perplexity Portable Computer Benchmark
Perplexity's Portable Computer offers private, cost-effective work with superior document understanding compared to open-source alternatives.
Perplexity Portable Computer uses a 27B model to score 82.6% on real knowledge work tasks. The product was benchmarked using ParseBench across tables, charts, layout, text content, and formatting. Perplexity's post-trained PPLX 27B model achieves 85.4% on the same benchmark. Document understanding capabilities depend on both the model and harness.
Big shoutout to @perplexity_ai for properly benchmarking document understanding in their Portable Computer release 🔥 They took a subset of our ParseBench benchmark parsebench.ai X) and measured across tables, charts, layout, text content, and formatting. Document understanding is the first step towards most knowledge work, and its capabilities are a function of both the model and harness. As companies build new models and agents that push the frontiers of knowledge work, we hope to see document understanding be a core part of any benchmarking effort. Perplexity @perplexity_ai New research: Portable Computer is a local-first agent for private and cost-effective work. With an on-device 27B model, our harness scores 82.6% on real knowledge work, beating open-source harnesses Pi and Hermes. Our post-trained PPLX 27B reaches 85.4%. 🔗 View Quoted Tweet 💬 2 🔄 2 ❤️ 3 👀 1147 📊 3 ⚡
