Apodex 1.1: benchmark results
Apodex US, Inc.'s proprietary agentic reasoning model, developed in the United States and Singapore. Apodex was founded by Tianqiao Chen; its open Apache-2.0 Apodex 1.1 Mini is a separate 35B-A3B checkpoint. Provider: Apodex. Released 2026-08-24. Access: API.
Aggregate Rating 1764 ± 27, rank #96 of 1635 rated models, from 51 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Long Context Reasoning | 79.33 | Accuracy (%) | 81.8 |
| AA GPQA Diamond | 86.36 | Accuracy (%) | 81.1 |
| AA Humanity's Last Exam | 34.06 | Accuracy (%) | 79.8 |
| AA GDP.pdf - HR - Criterion Pass Rate | 77.42 | Criterion Pass Rate (%) | 79.7 |
| AA MMMU-Pro | 79.19 | Accuracy (%) | 76.9 |
| AA CritPt | 4.57 | Accuracy (%) | 68.9 |
| AA Terminal-Bench 2.1 | 69.66 | Pass@1 (%) | 68.9 |
| AA APEX-Agents | 31.19 | Pass@1 (%) | 65.6 |
| AA GDP.pdf - Legal - Criterion Pass Rate | 76.71 | Criterion Pass Rate (%) | 63.7 |
| BenchLM | 54.6 | Overall Score | 62.1 |
| Apodex Discovery - AAV Tropism Prediction | 0.64 | Correlation (-1 to 1) between predicted and measured tissue | 61.1 |
| Tau3 Banking | 25.15 | Success Rate (%) | 59.9 |
Interactive version: theaggregate.ai/model?slug=apodex-1-1 · How It Works · Data refreshed daily, snapshot 2026-11-05.