Celeris-1: benchmark results
Provider: Celeris. Released 2026-07-23. Access: API.
Unified ELO 1489 ± 1, rank #921 of 1761 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Humanity's Last Exam | 6.81 | Accuracy (%) | 44.3 |
| BenchmarkList ECI | 106.56 | Capability Index (ECI) | 44.1 |
| AA GPQA Diamond | 63.13 | Accuracy (%) | 38.3 |
| Artificial Analysis Intelligence Index | 6.26 | Intelligence Index | 38.2 |
| AA Long Context Reasoning | 38 | Accuracy (%) | 38 |
| AA CritPt | 0 | Accuracy (%) | 24.4 |
| AA GDPval | 485.2 | ELO | 19.8 |
| AA Omniscience - Business | 10.51 | Accuracy (%) | 17 |
| AA Omniscience - Science, Engineering & Mathematics | 16.7 | Accuracy (%) | 15.5 |
| AA-Omniscience Accuracy | 10.98 | Accuracy (%) | 12.9 |
| AA Omniscience - Software Engineering (SWE) | 13.33 | Accuracy (%) | 12.1 |
| AA Omniscience - Health | 10.2 | Accuracy (%) | 11.9 |
Interactive version: theaggregate.ai/model?slug=celeris-1 · How It Works · Data refreshed daily, snapshot 2026-09-05.