ReasonEval-7B: benchmark results
Provider: Other.
Aggregate Rating 1430 ± 46, rank #4648 of 10916 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| GR-Ben - Chemistry | 27.3 | F1 (%) of first-error identification: the harmonic mean of t | 54.8 |
| PRMBench | 60.1 | Overall Score | 52 |
| GR-Ben - Inductive Reasoning | 22.4 | F1 (%) of first-error identification: the harmonic mean of t | 28.6 |
| GR-Ben - Physics | 24.5 | F1 (%) of first-error identification: the harmonic mean of t | 28.6 |
| GR-Ben | 17.5 | Average (self-reported) | 19 |
| GR-Ben - Analogical Reasoning | 20.4 | F1 (%) of first-error identification: the harmonic mean of t | 19 |
| GR-Ben - Computer Science | 17.5 | F1 (%) of first-error identification: the harmonic mean of t | 19 |
| GR-Ben - Mixed-Form Reasoning | 12.7 | F1 (%) of first-error identification: the harmonic mean of t | 19 |
| GR-Ben - Abductive Reasoning | 6.7 | F1 (%) of first-error identification: the harmonic mean of t | 9.5 |
| GR-Ben - Biology | 14.4 | F1 (%) of first-error identification: the harmonic mean of t | 9.5 |
| GR-Ben - Deductive Reasoning | 11.3 | F1 (%) of first-error identification: the harmonic mean of t | 7.1 |
Interactive version: theaggregate.ai/model?slug=reasoneval-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.