Pointwise Reasoning Evaluation on DeepfakeJudge Meta benchmark leaderboard · SOTA2 Research

Pointwise Reasoning Evaluation on DeepfakeJudge Meta

0.61RMSEDeepfakeJudge-7B

Evaluation Results

Method	Links
DeepfakeJudge-7B2026.02		0.61	0.37	0.94	0.93
DeepfakeJudge-3B2026.02		0.69	0.48	0.92	0.92
GPT-4o-Mini2026.02		0.78	0.6	0.87	0.87
Qwen-3-VL-235B-Thinking2026.02		1.01	1.02	0.84	0.84
Qwen-3-VL-30B-Thinking2026.02		1.02	1.05	0.83	0.83
Gemini-Flash-2.52026.02		1.09	1.2	0.82	0.83
Qwen-3-VL-8B-Thinking2026.02		1.09	1.19	0.83	0.82
Qwen-3-VL-235B-Instruct2026.02		1.1	1.21	0.83	0.82
Qwen-3-VL-8B-Instruct2026.02		1.19	1.41	0.76	0.75
Qwen-3-VL-30B-Instruct2026.02		1.28	1.65	0.81	0.81
Qwen-3-VL-4B-Instruct2026.02		1.59	2.53	0.57	0.58
Qwen-3-VL-2B-Instruct2026.02		1.6	2.55	0.6	0.61