Head-to-head
Loading model comparison.
Preparing shared benchmarks, gaps, and confidence notes.
Loading versus page
| Coding LB · % Code · Coding | 46.2%71.1% | 39.1%n/a | n/a |
| Reasoning LB · % Text · Reasoning / math / science | 46.4%63.1% | 42%n/a | n/a |
| Language LB · % Text · Chat / text | 32.1%54.6% | 30%n/a | n/a |
| Instruction following LB · % Text · Chat / text | 67.8%48.8% | 77.7%n/a | n/a |
| Coding generation LB · % Code · Coding | 42.3%63.8% | 36%n/a | n/a |
| Coding completion LB · % Code · Coding | 50%76.4% | 42.1%n/a | n/a |