Our new X account is live! Follow @wizwand_team for updates

Code Reasoning on HumanE

84.9Accuracy

Denser

Updated 4d ago

Evaluation Results

Method	Links
Denser 2025.12		84.9	-
Process Supervision 2025.12		84.6	-
Reflection-CoT 2025.12		84	-
Self-Verification 2025.12		83.7	-
Tree-of-Thought 2025.12		83.2	-
Denser 2025.12		83.1	-
Process Supervision 2025.12		82.9	-
Self-Consistency 2025.12		82.5	-
Reflection-CoT 2025.12		82.3	-
Self-Verification 2025.12		81.9	-
Think-to-Think 2025.12		81.8	-
Tree-of-Thought 2025.12		81.6	-
Self-Consistency 2025.12		80.9	-
Denser 2025.12		80.8	-
Process Supervision 2025.12		80.7	-
Think-to-Think 2025.12		80.2	-
Reflection-CoT 2025.12		80.1	-
Chain-of-Thought 2025.12		79.8	-
Self-Verification 2025.12		79.5	-
Tree-of-Thought 2025.12		78.9	-
Self-Consistency 2025.12		78.2	-
Chain-of-Thought 2025.12		78.2	-
Denser 2025.12		78.2	-58.7
Think-to-Think 2025.12		77.5	-
Self-Verification 2025.12		76.9	142.8
Process Supervision 2025.12		76.3	156.3
Chain-of-Thought 2025.12		75.8	-
TokenSkip (0.9 ratio) 2025.12		75.8	-53.5
Reflection-CoT 2025.12		75.4	127.6
Tree-of-Thought 2025.12		75	345.7
Self-Consistency 2025.12		74.1	289.4
Think-to-Think 2025.12		73.8	187.2
Chain-of-Thought (CoT) 2025.12		72.9	0
BeConcise 2025.12		71.5	-54.2
AbbreWords 2025.12		70.2	-50.8