VersaPRM (8B): benchmark results
Provider: Other.
Aggregate Rating 1555 ± 46, rank #1627 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| GR-Ben - Analogical Reasoning | 54.2 | F1 (%) of first-error identification: the harmonic mean of t | 95.2 |
| GR-Ben - Abductive Reasoning | 40 | F1 (%) of first-error identification: the harmonic mean of t | 85.7 |
| GR-Ben - Inductive Reasoning | 39.3 | F1 (%) of first-error identification: the harmonic mean of t | 81 |
| GR-Ben - Biology | 44.3 | F1 (%) of first-error identification: the harmonic mean of t | 76.2 |
| GR-Ben - Mixed-Form Reasoning | 41 | F1 (%) of first-error identification: the harmonic mean of t | 66.7 |
| GR-Ben | 34.1 | Average (self-reported) | 57.1 |
| GR-Ben - Physics | 31 | F1 (%) of first-error identification: the harmonic mean of t | 42.9 |
| GR-Ben - Computer Science | 23.3 | F1 (%) of first-error identification: the harmonic mean of t | 33.3 |
| GR-Ben - Chemistry | 22.4 | F1 (%) of first-error identification: the harmonic mean of t | 19 |
| GR-Ben - Deductive Reasoning | 11.3 | F1 (%) of first-error identification: the harmonic mean of t | 7.1 |
Interactive version: theaggregate.ai/model?slug=versaprm-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.