Sarcasm Detection on MMSD 1.0 (test) benchmark leaderboard · SOTA2 Research

Sarcasm Detection on MMSD 1.0 (test)

86.7F1 ScoreCommander

Evaluation Results

Method
Commander2025.06	86.7	90.1	87.4	86.1
Commander2025.06	81.4	83.1	78.9	84.2
BERT (Fine-tuned)2025.06	80.8	82.6	81.2	80.1
S^3 Agent2025.06	77.9	80.2	74.6	81.5
Generated Knowledge Prompting2025.06	76.3	79.7	73.5	79.2
Automatic Prompt Engineer2025.06	75.8	79.1	72.9	78.9
Zero-shot CoT2025.06	74.2	78.5	71.3	77.4
Commander2025.06	73.8	76.2	70.1	78.3
Plan-and-Solve2025.06	73.6	77.8	70.2	77.1
Commander2025.06	72.5	74.5	65.9	80.8
S^3 Agent2025.06	70.1	74.9	67.8	75.7
Generated Knowledge Prompting2025.06	69.5	73.6	66.3	74.2
Commander2025.06	69.3	68.2	58	86.2
Automatic Prompt Engineer2025.06	68.7	72.8	64.1	73.9
S^3 Agent2025.06	68.1	67.5	57.6	83.3
Zero-shot CoT2025.06	67.2	71.4	62.8	70.5
Zero-shot CoT2025.06	66.4	66	56.5	80.7
Plan-and-Solve2025.06	66.3	70.2	62.5	71.8
Automatic Prompt Engineer2025.06	64.5	60.5	51.6	86
Automatic Prompt Engineer2025.06	63.2	69.2	63.1	63.4
Generated Knowledge Prompting2025.06	63.2	67.5	59.9	66.8
Zero-shot CoT2025.06	61.4	68.1	62.1	60.7
Commander2025.06	61.1	69.4	64.9	57.7
Plan-and-Solve2025.06	60.9	66	58.5	63.5
S^3 Agent2025.06	60.8	66.6	59.6	62
S^3 Agent2025.06	59.7	45.3	43.1	59.7
Plan-and-Solve2025.06	59.4	64.8	57.2	61.8
Commander2025.06	59.1	70.8	71.2	50.5
Generated Knowledge Prompting2025.06	55.6	56.8	48.7	65
Automatic Prompt Engineer2025.06	55.1	68	66.4	47.6
Plan-and-Solve2025.06	54.9	61.9	54.3	55.5
Zero-shot CoT2025.06	54.4	65.3	60.1	49.8
Generated Knowledge Prompting2025.06	52.7	55.7	47.5	59.2
S^3 Agent2025.06	52.3	41.4	39.6	77
Plan-and-Solve2025.06	51.3	62.6	56.2	47.2
Generated Knowledge Prompting2025.06	50.9	67.1	64.7	40.9
Automatic Prompt Engineer2025.06	49.4	53.3	45	54.7
Zero-shot CoT2025.06	45.8	59.2	51.4	41.4