Misinformation Detection on AMTCele

88.88AccuracyGPT4o

Evaluation results

Method
GPT4o2024.06	88.88	89.34	88.88	88.84
GPT4o2024.06	88.47	89.12	88.47	88.42
GPT4o2024.06	88.16	88.56	88.16	88.13
GPT4o2024.06	87.76	88.5	87.76	87.7
GPT4o2024.06	87.24	88.24	87.24	87.16
Deepseek-R2026.01	86.8	87.1	86.8	86.8
Deepseek-C2026.01	86.2	86.4	86.2	86.2
gpt-4.12026.01	85.6	86.2	85.6	85.5
Deepseek-C2026.01	84.6	85.6	84.6	84.5
RAAR-14b2026.01	84.2	84.2	84.2	84.2
Deepseek-R2026.01	83.2	83.3	83.2	83.2
gpt-4.12026.01	82	84.7	82	81.6
Llama-8b2026.01	82	54.9	54.7	54.8
RAAR-8b2026.01	81.2	81.3	81.2	81.2
RAEmoLLM2026.01	80.8	84.3	80.8	80.3
Qwen-32b2026.01	80.4	80.4	80.4	80.4
gpt-5-mini2026.01	79	79.2	79	79
Qwen-8b2026.01	78.6	79.9	78.6	78.4
IT_zs2026.01	78.4	79.4	78.4	78.2
Qwen-14b2026.01	78.2	78.5	78.2	78.1
gpt-5-mini2026.01	78	78	78	78
Qwen-8b2026.01	77.6	77.9	77.6	77.5
Mistral-7b2024.06	77.35	78.22	77.35	77.17
IT_ra2026.01	75	50.9	50	50.3
Mistral-7b2024.06	74.69	77.48	74.69	74.04
Qwen-14b2026.01	74.2	76.5	74.2	73.6
Qwen-32b2026.01	74.2	75.7	74.2	73.8
ChatGPT2024.06	72.65	74.2	72.65	72.21
ChatGPT2024.06	71.63	76.28	71.63	70.32
Mistral-7b2024.06	70.82	77.68	70.82	68.89
EDDFN2024.06	70.41	73.13	70.41	69.51
Mistral-7b2024.06	70.2	73.46	70.2	69.26
ChatGPT2024.06	69.9	74.75	69.9	68.35
ChatGPT2024.06	69.59	71.93	69.59	68.76
MARO2026.01	68.8	—	—	68
EDDFN2026.01	68	68.6	68	67.8
ChatGPT2024.06	67.45	73.66	67.45	65.16
Llama-8b2026.01	66.6	55.4	44.4	48.9
MetaAdapt2024.06	64.29	65.64	64.29	63.5
Llama3.2-1b2024.06	64.29	64.6	64.29	64.38
MDFEND2026.01	64.2	66.3	64.2	63
Mistral-7b2024.06	63.37	70.5	63.37	59.88
Vicuna-7b2024.06	63.16	66.8	63.16	62.48
CANMD2024.06	62.96	66.5	62.96	60.86
Gemma-2b2024.06	62.35	62.98	62.35	62.13
Llama3.2-1b2024.06	61.73	63.6	61.73	60.65
MetaAdapt2026.01	60.8	57.6	82	67.7
Vicuna-7b2024.06	60	60.69	60	60.23
MDFEND2024.06	58.78	59.34	58.78	58.15
Gemma-2b2024.06	58.47	61.9	58.47	55.25
Vicuna-7b2024.06	58.37	58.72	58.37	58.06
RoBERTa2024.06	56.78	72.28	56.78	47.3
Vicuna-7b2024.06	56.22	60.4	56.22	52.06
Vicuna-7b2024.06	54.9	55.45	54.9	53.84
BERT2024.06	54.14	54.53	54.14	53.22
Llama3.2-1b2024.06	53.98	54.83	53.98	52.22
CANMD2026.01	50.4	75.1	50.4	34.2
MOSE2024.06	50.31	50.51	50.31	44.82
Gemma-2b2024.06	49.8	49.97	49.8	46.49
Gemma-2b2024.06	49.29	49.28	49.29	49.27
MOSE2026.01	49.2	24.8	49.2	33
Llama3.2-1b2024.06	48.67	48.68	48.67	47.82
Llama3.2-1b2024.06	47.96	48.41	47.96	48.01
Gemma-2b2024.06	41.53	45.68	41.53	38.15