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

Commonsense Reasoning on PIQA, WinoG., HellaS., BoolQ, SIQA, OBQA (test)

89.9PIQA Accuracy

LLMBOOST

Updated 3d ago

Evaluation Results

Method	Links
LLMBOOST 2025.12		89.9	88.8	95.4	74.4	81.2	91.4	86.9
LLMBOOST 2025.12		89.5	86.7	95.1	71.6	79.1	91.6	85.6
LLMBOOST 2025.12		87.9	86.1	94.5	71.7	81.6	85.6	84.4
vote 2025.12		87.7	83.2	90.3	71.8	80.4	85.4	83.1
vote 2025.12		87.5	82.2	91.3	70.2	79.6	85.8	82.7
LLMBOOST 2025.12		87.4	86.3	95.2	72.5	80.7	84.8	84.5
T-copilot 2025.12		87.1	84.3	90.2	70.8	79.3	89.2	83.5
UNITE 2025.12		86.9	84.9	93.5	70.5	79.2	84.8	83.3
Qwen-2.5-7B 2025.12		86.7	83.9	89.4	68.7	77.6	87.4	82.3
vote 2025.12		86.3	84.5	91.3	70.7	80	88.8	83.6
UNITE 2025.12		86.1	84.1	91.6	68.6	79.1	88.2	83
UNITE 2025.12		86.1	83.3	91.5	70.3	78.4	86.8	82.7
LLMBOOST 2025.12		86.1	82	91.7	70.4	80	87.6	83
LLMBOOST 2025.12		85.9	81.8	91.4	69.7	79	86.2	82.3
UNITE 2025.12		85.3	85	92.2	70.9	79.9	85	83.1
UNITE 2025.12		84.8	80.8	85.1	66.2	77.3	86	80
LLMBOOST 2025.12		84.7	81.4	90.4	67.1	78	78.8	80.1
Qwen-2.5-3B 2025.12		84.5	80.1	80.6	68.1	77.7	84.6	79.3
T-copilot 2025.12		84.2	83.2	91.4	69.8	76.9	78.4	81
LLMBOOST 2025.12		84.2	82	91.5	70.2	79	79.6	81.1
UNITE 2025.12		84.1	80.6	83.5	67.3	78	83	79.4
vote 2025.12		84.1	79.7	87.6	67.8	77.4	83.8	80.4
T-copilot 2025.12		83.9	80.2	82.6	68.9	78.4	86.4	80.1
vote 2025.12		83.4	80	86.3	68.7	77.9	84	80.1
Llama-3.1-8B 2025.12		83.3	81.8	90.6	69.5	75.8	79	80
UNITE 2025.12		82.8	80	88.7	66.5	76.7	77.4	78.7
UNITE 2025.12		82.8	81.3	89.9	67.1	78.4	78.2	79.6
vote 2025.12		81.7	81.3	86.8	67.3	76.1	84.8	79.7
vote 2025.12		80.5	76.4	85.1	66.7	77.5	77.2	77.2
vote 2025.12		79.4	76.9	84.7	66.2	75.4	75.8	76.4
LLama-3.2-3B 2025.12		78.5	77.7	83.9	62.4	74.3	76.8	75.6
T-copilot 2025.12		75.7	75.9	83.4	64.6	73.8	77.2	75.1