DALPHIN (Independent) - Neoplastic Behavior: leaderboard
Classifying the ICD-O-3 behavior of the lesion (benign, uncertain, in situ or malignant) for the 224 neoplastic cases of the DALPHIN pathology copilot benchmark (Lems et al., 2026). Cohen's kappa against the pathologist reference (-1 to 1); higher is better. Independent scenario: every question is sent as a standalone query without earlier answers.
Metric: Cohen's kappa (-1 to 1; ICD-O-3 behavior of the lesion: benign, uncertain, in situ or malignant, 224 neoplastic cases, tissue type given; independent scenario: each question asked as a standalone query). Source: arxiv.org. Saturation forecast: Around February 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro (Medium) | 0.46 | #262 (Gemini 2.5 Pro) |
| 2 | GPT-5 (Medium) | 0.27 | #163 (GPT-5) |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=dalphin-independent-neoplastic-behavior · How It Works · Data refreshed daily, snapshot 2026-11-12.