Top-tier model from OpenAI (ECI 138). solid benchmark performance. strong intelligence. Released Apr 2025. API access.
Epoch Capabilities Index score
Normalized ECI score (0-100)
Total compute used during training
Organization that created the model
Model development country
Access method (API, download, etc.)
Model weights publicly available
Epoch AI benchmark identifier
Code generation, understanding, and debugging
Mathematical reasoning and problem solving
Multi-step logical reasoning
Overall reasoning and task completion ability
| Dimension | Score |
|---|---|
| Intelligence | 86.0 |
| Reasoning | 82.0 |
| Math | 77.0 |
| Code | 73.0 |
| Instruction Following | 77.0 |
| Overall | 86 |