Baba Is Harbor - Stage 0: leaderboard
Tests agents playing Baba Is You across eight introductory levels using the same harness for every model. Reports the percentage of levels solved in stage 0; later stages using different model-specific harnesses are excluded from this series.
Metric: pass@1 (%). Source: quesma.com. Saturation forecast: Around February 2027. 29 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 100 | #33 |
| 2 | GPT-5.6 Sol | 100 | #22 |
| 3 | Claude Opus 5 | 100 | #16 |
| 4 | Gemini 3.8 Flash | 100 | #30 |
| 5 | GPT-6 Astra | 100 | #6 |
| 6 | Claude Fable 5 | 100 | #20 |
| 7 | Gemini 3.7 Flash | 100 | #24 |
| 8 | Claude Fable 5.1 | 100 | #10 |
| 9 | Claude Opus 4.8 | 96 | #39 |
| 10 | Kimi K3 | 96 | #35 |
| 11 | GLM-5.2 | 96 | #80 |
| 12 | GLM-5.3 | 96 | #44 |
| 13 | Grok 4.6 | 96 | #29 |
| 14 | Gemini 3.1 Pro (Preview) | 92 | #64 |
| 15 | GPT-5.6 Terra | 88 | #40 |
No result here: #3 Claude Opus 5.5, #7 GPT-6.1 Sol, #9 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=baba-is-harbor-stage-0 · How It Works · Data refreshed daily, snapshot 2026-11-05.