Agnes 2.5 Pro Theta: benchmark results
Provider: Sapiens AI. Released 2026-11-07.
Aggregate Rating 1775 ± 23, rank #130 of 10870 rated models, from 73 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Long Context Reasoning | 84.67 | Accuracy (%) | 98.9 |
| AA-Briefcase - PDF - Rubric Pass Rate | 56.9 | Rubric Pass Rate (%) | 88.1 |
| AA-Briefcase - XLSX - Rubric Pass Rate | 53.9 | Rubric Pass Rate (%) | 86.5 |
| AA-Briefcase - Analytical Quality Elo | 1709.99 | Elo | 86.2 |
| AA GDP.pdf - HR - Criterion Pass Rate | 78.89 | Criterion Pass Rate (%) | 84.2 |
| AA-Omniscience Hallucination Rate | 43.74 | Hallucination Rate (%) | 83.7 |
| AA-Briefcase | 52 | Rubric Pass Rate (%) | 82.7 |
| AA GDP.pdf - Insurance - Criterion Pass Rate | 80.03 | Criterion Pass Rate (%) | 82.6 |
| AA Humanity's Last Exam | 37.16 | Accuracy (%) | 82.3 |
| AA CritPt | 15.14 | Accuracy (%) | 81.7 |
| AA GDPval | 1507 | ELO | 80.6 |
| AA SciCode | 56.02 | Accuracy (%) | 80.5 |
Interactive version: theaggregate.ai/model?slug=agnes-2-5-pro-theta · How It Works · Data refreshed daily, snapshot 2026-11-12.