SPHINX-v2: benchmark results
Provider: Other.
Aggregate Rating 1325 ± 46, rank #8251 of 10916 rated models, from 4 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| TempCompass | 51.92 | Avg All (%) | 35.7 |
| CharXiv-R | 16.1 | Validation chart-visible reasoning accuracy (%) | 13.8 |
| CharXiv-D | 30.25 | Score (%) | 13.3 |
| MathVision | 9.7 | Overall Accuracy (%) | 1.3 |
Interactive version: theaggregate.ai/model?slug=sphinx-v2 · How It Works · Data refreshed daily, snapshot 2026-11-08.