Baba Is Harbor - Stage 0: leaderboard

Metric: pass@1 (%). Source: quesma.com. 29 models tracked.

Top models

#ModelScore
1GPT-5.5100
2GPT-5.6 Sol100
3Claude Opus 5100
4Claude Fable 5100
5GPT-6100
6Gemini 3.7 Flash100
7Gemini 3.8 Flash100
8Claude Fable 5.1100
9Claude Opus 4.896
10Kimi K396
11GLM-5.296
12GLM-5.396
13Grok 4.696
14Gemini 3.1 Pro (Preview)92
15GPT-5.6 Terra88

Interactive version: theaggregate.ai/benchmark?slug=baba-is-harbor-stage-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.