Bijural Equivalence
Map common law concepts to their civil law equivalents — testing Canada's unique bijural legal system.
Judge-scored column: scores are strict accuracy — a record counts only when the judge gives it full credit (verdict 1.0) — since 2026-10-05. The lenient pass rate (verdict ≥ 0.5, half credit counted) is shown beside each model.
175 records|5 models evaluated|Best: 57.1%|Worst: 33.1%
Model Performance (avg 50.2%)
1
GPT-5.6 Sol
175 records · 100 correct
57.1%
strict · lenient 78.9%
2
Gemini 3.1 Pro
175 records · 98 correct
56.0%
strict · lenient 79.4%
3
Claude Fable 5
175 records · 96 correct
54.9%
strict · lenient 78.9%
4
Grok 4.5
175 records · 87 correct
49.7%
strict · lenient 75.4%
5
Cohere Command A+
175 records · 58 correct
33.1%
strict · lenient 58.9%