PathChat+: benchmark results
Provider: Other.
Aggregate Rating 1735 ± 51, rank #222 of 10916 rated models, from 16 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| DALPHIN (Contextual) - Diagnosis | 0.85 | BioBERT semantic similarity (biomedical sentence-embedding s | 100 |
| DALPHIN (Contextual) - Multiple Choice | 0.78 | Accuracy (0-1; one case-specific multiple-choice question pe | 100 |
| DALPHIN (Contextual) - Neoplasm Detection | 0.86 | Matthews correlation coefficient (-1 to 1; is a neoplasm pre | 100 |
| DALPHIN (Contextual) - Neoplastic Behavior | 0.63 | Cohen's kappa (-1 to 1; ICD-O-3 behavior of the lesion: beni | 100 |
| DALPHIN (Contextual) - Organ Recognition | 0.79 | Organ recognition score (0-1; free-response organ or residua | 100 |
| DALPHIN (Independent) - Diagnosis | 0.83 | BioBERT semantic similarity (biomedical sentence-embedding s | 100 |
| DALPHIN (Independent) - Neoplasm Detection | 0.74 | Matthews correlation coefficient (-1 to 1; is a neoplasm pre | 100 |
| DALPHIN (Independent) - Neoplastic Behavior | 0.57 | Cohen's kappa (-1 to 1; ICD-O-3 behavior of the lesion: beni | 100 |
| DALPHIN (Independent) - Organ Recognition | 0.77 | Organ recognition score (0-1; free-response organ or residua | 100 |
| VIPER (Veterinary Pathology) - Free-Text | 52.7 | Free-text score (0-100), a composite rubric grade by a GPT-5 | 80 |
| VIPER (Veterinary Pathology) - MCQ | 58.7 | Multiple-choice accuracy (%; five options, mean over five cy | 73.3 |
| VIPER (Veterinary Pathology) | 51 | Overall score (%; mean of the MCQ, KPrim and free-text score | 66.7 |
Interactive version: theaggregate.ai/model?slug=pathchat-plus · How It Works · Data refreshed daily, snapshot 2026-11-08.