Share your thoughts, 1 month free Claude Pro on usSee more

Logical Reasoning on ZebraLogic v1.0 (test)

97.7Cell Accuracy

In-place

Updated 5d ago

Evaluation Results

Method	Links
In-place 2025.10		97.7
In-place 2025.10		97.2
In-place 2025.10		96.8
In-place 2025.10		96.3
Multi-turn 2025.10		95.9
In-place 2025.10		95.6
Multi-turn 2025.10		94.7
In-place 2025.10		94.4
Multi-turn 2025.10		93.5
In-place 2025.10		93.1
Multi-turn 2025.10		92.7
Multi-turn 2025.10		92.1
In-place 2025.10		91.4
Multi-turn 2025.10		89.6
Multi-turn 2025.10		89.1
Memory 2025.10		89.1
In-place 2025.10		89.1
Memory 2025.10		88.9
In-place 2025.10		88.3
Memory 2025.10		87.1
Memory 2025.10		86.6
In-place 2025.10		85.9
Multi-turn 2025.10		85.9
Multi-turn 2025.10		84.8
In-place 2025.10		84.7
Memory 2025.10		84.1
Memory 2025.10		83.5
In-place 2025.10		83.3
In-place 2025.10		83
Memory 2025.10		80.7
Multi-turn 2025.10		80.6
In-place 2025.10		79.8
In-place 2025.10		79.4
Memory 2025.10		79.4
Multi-turn 2025.10		77.9
Memory 2025.10		75.8
In-place 2025.10		75.1
Memory 2025.10		75
In-place 2025.10		73.8
Multi-turn 2025.10		73.6
Multi-turn 2025.10		71.8
Multi-turn 2025.10		70.1
In-place 2025.10		69.8
Memory 2025.10		69.3
Memory 2025.10		69
Multi-turn 2025.10		68.1
In-place 2025.10		67.9
Multi-turn 2025.10		67.1
Multi-turn 2025.10		66.3
Multi-turn 2025.10		65.2
Memory 2025.10		61.8
Multi-turn 2025.10		61.2
In-place 2025.10		60.7
Memory 2025.10		60.3
Memory 2025.10		59.9
In-place 2025.10		59.1
Memory 2025.10		58.6
In-place 2025.10		57.3
Memory 2025.10		57.1
Multi-turn 2025.10		56.7
Memory 2025.10		54.8
Multi-turn 2025.10		54.6
Multi-turn 2025.10		54.3
Memory 2025.10		52.8
Memory 2025.10		51.8
Memory 2025.10		50.5
Memory 2025.10		48.7
In-place 2025.10		48
Memory 2025.10		46.4
Multi-turn 2025.10		46
In-place 2025.10		44.3
Multi-turn 2025.10		43.5
In-place 2025.10		43.2
Multi-turn 2025.10		41.7
Memory 2025.10		41.1
Memory 2025.10		40.6
In-place 2025.10		36.7
Multi-turn 2025.10		36.6
Memory 2025.10		35
Memory 2025.10		33.9
Multi-turn 2025.10		27.2
Memory 2025.10		27.2
In-place 2025.10		27.2
Memory 2025.10		26.4
In-place 2025.10		26.4
Multi-turn 2025.10		26.3
Multi-turn 2025.10		19.1
Memory 2025.10		19.1
In-place 2025.10		19.1
Multi-turn 2025.10		18.5