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

Logical Reasoning on ZebraLogic

98.8Accuracy

GPT-5 (High)

Updated 1mo ago

Evaluation Results

Method	Links
GPT-5 (High) 2026.02		98.8
DS V3.2-Thinking 2026.02		97.6
ERNIE 5.0 2026.02		96.5
Gemini 3-Pro 2026.02		95.5
Gemini 2.5-Pro 2026.02		92.9
VERGE Full 2026.01		91
VERGE w/o Rt 2026.01		90.9
VERGE w/o MCS 2026.01		88.9
VERGE Full 2026.01		87.3
Qwen 3 VL 32B Instruct 2025.12		86.7
CoT 2026.01		84
VERGE w/o Rt 2026.01		83.6
VERGE w/o MCS 2026.01		80.9
SC 2026.01		77.8
SC 2026.01		72.2
SR 2026.01		72.2
CoT 2026.01		67.6
VERGE Full 2026.01		64.8
VERGE w/o Rt 2026.01		62.8
Olmo 3.1 32B Instruct 2025.12		61.7
SR 2026.01		58.8
VERGE w/o MCS 2026.01		58
CoT 2026.01		52
Olmo 3.1 32B Instruct 2025.12		51.1
SC 2026.01		51
DSB 2026.01		48
SR 2026.01		46.2
DSB 2026.01		44.8
Bridge 2025.10		44.7
P-Match 2025.10		43.5
RLVR 2025.10		43.25
P-Match 2025.10		42.95
Bridge 2025.10		42.6
RLVR 2025.10		41.25
DS-Llama-8B 2025.10		41.25
DS-Qwen-7B 2025.10		40
Bridge 2025.10		33.15
P-Match 2025.10		32.55
DS-Qwen-1.5B 2025.10		30.9
RLVR 2025.10		30.9
Olmo 3.1 32B Instruct 2025.12		30.6
Qwen 3 32B 2025.12		28.4
DSB 2026.01		28.2
Gemma 3 27B 2025.12		24.8
Qwen 2.5 32B 2025.12		24.1
Gemma 2 27B 2025.12		17.2
OLMo 2 32B 2025.12		13.3
Apertus 70B 2025.12		9