| model \ task | web-platformer |
|---|---|
| qwen3.6-27b | 5/5 graded · 40% |
| gemma-4-31b | 5/5 graded · 70% |
| qwen3.6-35b-a3b | 5/5 graded · 30% |
| ornith-1.0-35b | 5/5 graded · 30% |
| north-mini-code-1.0 | 5/5 graded · 20% |
| bielik-11b-v3 | 5/5 graded · 0% |
Cells show passes / repetitions. Click a cell for the produced code, transcript and verify output.