Agnes 2.5 Pro Alpha: benchmark results
Provider: Other. Released 2026-07-24. Access: API.
Unified ELO 1641 ± 1, rank #280 of 1761 rated models, from 18 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BenchmarkList ECI | 137.02 | Capability Index (ECI) | 86.4 |
| AA CritPt | 10.86 | Accuracy (%) | 86.3 |
| AA Humanity's Last Exam | 33.6 | Accuracy (%) | 85.1 |
| AA GPQA Diamond | 87.58 | Accuracy (%) | 84 |
| AA Omniscience - Science, Engineering & Mathematics | 43.5 | Accuracy (%) | 83.7 |
| Artificial Analysis Intelligence Index | 31.25 | Intelligence Index | 82.5 |
| AA Long Context Reasoning | 75.67 | Accuracy (%) | 78.8 |
| AA Omniscience - Humanities & Social Sciences | 33.3 | Accuracy (%) | 78.8 |
| AA Omniscience - Health | 32.2 | Accuracy (%) | 77.6 |
| AA-Omniscience Accuracy | 33.48 | Accuracy (%) | 77.4 |
| AA Omniscience - Law | 25.1 | Accuracy (%) | 76.5 |
| AA Omniscience - Business | 25.4 | Accuracy (%) | 75 |
Interactive version: theaggregate.ai/model?slug=agnes-2-5-pro-alpha · How It Works · Data refreshed daily, snapshot 2026-09-05.