Qwen2.5-Math-SCAN-Pro-7B: benchmark results
Provider: Alibaba.
Aggregate Rating 1423 ± 51, rank #5026 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| GR-Ben - Chemistry | 27.8 | F1 (%) of first-error identification: the harmonic mean of t | 61.9 |
| GR-Ben - Physics | 31.8 | F1 (%) of first-error identification: the harmonic mean of t | 52.4 |
| GR-Ben - Abductive Reasoning | 14.2 | F1 (%) of first-error identification: the harmonic mean of t | 42.9 |
| GR-Ben - Analogical Reasoning | 34.2 | F1 (%) of first-error identification: the harmonic mean of t | 38.1 |
| GR-Ben | 19.8 | Average (self-reported) | 28.6 |
| GR-Ben - Biology | 20.3 | F1 (%) of first-error identification: the harmonic mean of t | 28.6 |
| GR-Ben - Deductive Reasoning | 13.1 | F1 (%) of first-error identification: the harmonic mean of t | 26.2 |
| GR-Ben - Computer Science | 15.3 | F1 (%) of first-error identification: the harmonic mean of t | 14.3 |
| GR-Ben - Mixed-Form Reasoning | 8.6 | F1 (%) of first-error identification: the harmonic mean of t | 14.3 |
| GR-Ben - Inductive Reasoning | 12.7 | F1 (%) of first-error identification: the harmonic mean of t | 9.5 |
Interactive version: theaggregate.ai/model?slug=qwen2-5-math-scan-pro-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.