txgemma-9B-chat: benchmark results
Provider: Other.
Aggregate Rating 1330 ± 40, rank #8167 of 10916 rated models, from 16 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MedPRMBench (Step Probability) | 57.7 | PRMScore (%): mean of the F1 for erroneous steps and the F1 | 90.9 |
| MolecularIQ - Counting | 4.1 | Mean Accuracy (%) | 17.6 |
| MolecularIQ - Indexing | 0.5 | Mean Accuracy (%) | 17.6 |
| MolecularIQ - Generation | 3.1 | Mean Accuracy (%) | 13.5 |
| MolecularIQ - Overall | 2.6 | Mean Accuracy (%) | 13.5 |
| SurgiQ | 28.82 | Micro accuracy over all 13,055 questions: accuracy (%) on Su | 8.8 |
| SurgiQ - Best-Option | 27.27 | Best-option questions (2,085), several options partly correc | 8.8 |
| SurgiQ - Case-Based | 28.24 | Case-based questions (6,156): accuracy (%) on SurgiQ's four- | 8.8 |
| SurgiQ - General Surgery | 28.45 | General surgery questions (6,948): accuracy (%) on SurgiQ's | 8.8 |
| SurgiQ - Laparoscopic Surgery | 30.83 | Laparoscopic surgery questions (493): accuracy (%) on SurgiQ | 8.8 |
| SurgiQ - Negative | 31.78 | Negative (all-except) questions (2,153): accuracy (%) on Sur | 8.8 |
| SurgiQ - Neurosurgery | 28.77 | Neurosurgery questions (2,204): accuracy (%) on SurgiQ's fou | 8.8 |
Interactive version: theaggregate.ai/model?slug=txgemma-9b-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.