Head-to-head
Loading model comparison.
Preparing shared benchmarks, gaps, and confidence notes.
Loading versus page
| Coding LB · % Code · Coding | 67.4%94.5% | 39.1%n/a | n/a |
| Reasoning LB · % Text · Reasoning / math / science | 59.2%89.2% | 42%n/a | n/a |
| Language LB · % Text · Chat / text | 52.1%93.1% | 30%n/a | n/a |
| Instruction following LB · % Text · Chat / text | 80.6%84% | 77.7%n/a | n/a |
| Coding generation LB · % Code · Coding | 80.8%96.9% | 36%n/a | n/a |
| Coding completion LB · % Code · Coding | 54%81.1% | 42.1%n/a | n/a |