DALPHIN (Contextual) - Open Questions: leaderboard

Metric: BioBERT semantic similarity (biomedical sentence-embedding similarity, at most 1) of the uncurated free-text answer to the contributing pathologist's reference answer (285 case-specific free-response questions; contextual scenario: all questions of a case asked in sequence in one conversation). Source: arxiv.org. Saturation forecast: Around January 2028. 3 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro (Medium)0.64
2GPT-5 (Medium)0.62

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