PiSAR: leaderboard

Metric: Semantic similarity (mean cosine similarity between OpenAI text-embedding-3-small embeddings of the predicted and the gold rationale; 661 held-out rows: 119 OPeRA shopping traces and 542 app-store reviews). Source: arxiv.org. Saturation forecast: Around April 2028. 5 models tracked.

Top models

#ModelScore
1GPT-5.50.48
2Claude Opus 4.70.46

Interactive version: theaggregate.ai/benchmark?slug=pisar · How It Works · Data refreshed daily, snapshot 2026-09-26.