aion-labs
Comparing 3 models from aion-labs.
| Model | Total ▼ | Released | Context | CoT | Tooling | Creative Writing | Language | Utility | Reasoning | Text Editing | Rule Following | Hallucination |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Aion 3.0 | 88.78% | May 5, 26 | 128k | ✓ | 96.54% | 84.64% | 86.85% | 93.57% | 86.56% | 97.73% | 68.80% | 95.57% |
| Aion 2.0 | 86.66% | Feb 23, 26 | 128k | ✓ | 95.10% | 80.24% | 96.17% | 90.91% | 78.64% | 95.34% | 63.77% | 93.10% |
| Aion 3.0 Mini | 83.69% | May 14, 26 | 128k | ✓ | 75.94% | 84.60% | 93.68% | 90.76% | 75.86% | 93.65% | 60.98% | 94.08% |
Model Performance
Cost vs Performance
Compares total benchmark cost against overall score for aion-labs models. Quadrant lines are drawn at the median values.
Cost Breakdown
Total benchmark cost per model, broken down by input, reasoning, and output tokens. Toggle between USD and token views.