Share your thoughts, 1 month free Claude Pro on usSee more

Deception Detection on Varied Deception

0.95Apollo Score

GLM-4.7-FP8

Updated 1mo ago

Evaluation Results

Method	Links
GLM-4.7-FP8 2026.06		0.95	0.42	0.93	0.98	0.88
Qwen3.5-27B 2026.06		0.95	0.42	0.93	0.97	0.76
gemma-4-31B-it 2026.06		0.95	0.39	0.68	0.98	0.94
GLM-5-FP8 2026.06		0.94	0.5	0.9	0.98	0.9
GLM-5.1-FP8 2026.06		0.91	0.51	0.89	0.98	0.89
gemma-4-26B-A4B-it 2026.06		0.91	0.31	0.77	0.96	0.93
GLM-4.5-Air-FP8 2026.06		0.9	0.23	0.84	0.96	0.77
Kimi-K2.5 2026.06		0.89	0.47	0.78	0.99	0.83
Qwen3.5-4B 2026.06		0.89	0.27	0.82	0.92	0.81
Qwen3.5-35B-A3B-FP8 2026.06		0.88	0.37	0.88	0.95	0.87
Qwen3.6-35B-A3B 2026.06		0.87	0.44	0.86	0.97	0.89
Qwen3-14B 2026.06		0.87	0.16	0.8	0.92	0.76
Qwen3.5-122B-A10B-FP8 2026.06		0.86	0.42	0.92	0.98	0.89
Qwen3-30B-A3B 2026.06		0.86	0.15	0.82	0.92	0.83
DeepSeek-V3.2 2026.06		0.85	0.42	0.87	0.96	0.85
GLM-4.7-Flash 2026.06		0.85	0.3	0.88	0.96	0.84
Kimi-K2.6 2026.06		0.84	0.54	0.73	0.98	0.78
Qwen3.6-27B 2026.06		0.84	0.46	0.88	0.95	0.8
Llama-3.3-70B-Instruct 2026.06		0.84	0.14	0.74	0.53	0.84
MiniMax-M2.7 2026.06		0.83	0.5	0.84	0.86	0.78
MiMo-V2-Flash 2026.06		0.83	0.39	0.83	0.9	0.81
gemma-4-E4B-it 2026.06		0.83	0.19	0.82	0.96	0.78
gemma-3-27b-it 2026.06		0.81	0.1	0.78	0.6	0.78
gpt-oss-120b 2026.06		0.8	0.33	0.72	0.97	-
gemma-4-E2B-it 2026.06		0.79	0.15	0.76	0.94	0.81
gemma-2-9b-it 2026.06		0.77	-	0.7	0.52	0.77
gpt-oss-20b 2026.06		0.75	0.24	0.74	0.94	-
Qwen3-32B 2026.06		0.74	0.16	0.76	0.92	0.78
Qwen3-8B 2026.06		0.74	0.13	0.69	0.87	0.76
gemma-3-12b-it 2026.06		0.74	0.09	0.72	0.59	0.79
MiniMax-M2 2026.06		0.72	0.36	0.74	0.74	-
Qwen3-4B 2026.06		0.64	0.14	0.68	0.85	0.74