OpenAI's frontier model ranking ECI 152. exceptional across reasoning, coding, and math benchmarks. exceptional math.
Metrics
ELO1,486
LMArena human preference ranking
ECI Score152.418
Epoch Capabilities Index score
ECI Normalized98
Normalized ECI score (0-100)
Context Window400,000
Maximum input token capacity
Training Compute6.6e25 FLOP
Total compute used during training
Score Breakdown
code
20%100
Code generation, understanding, and debugging
math
20%100
Mathematical reasoning and problem solving
reasoning
15%100
Multi-step logical reasoning
intelligence
30%98
Overall reasoning and task completion ability
Compatibility(3)
Developed by
OpenAIBenchmark Performance
Compare ModelsEpoch Capabilities Index
152.4/ 155
| Dimension | Score |
|---|---|
| Intelligence | 98.0 |
| Reasoning | 100.0 |
| Math | 100.0 |
| Code | 100.0 |
| Overall | 98 |
Loading chart...
Data: Epoch AI (CC-BY 4.0)