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

Identity Judgment on MISID

72.22Identity Judgment Accuracy

DeepSeek-R1

Updated 4d ago

Evaluation Results

Method	Links
DeepSeek-R1 2026.04		72.22	63.87
DeepSeek-R1 2026.04		65.38	56.54
Claude-Sonnet-4.5 2026.04		61.96	56.53
DeepSeek-V3 2026.04		61.69	57.83
Grok-4-Fast 2026.04		57.69	47.62
GPT-5.1 2026.04		56.93	58.41
Grok-4-Fast 2026.04		55.56	49.75
GLM-4.7 2026.04		55.01	55
GPT-4o 2026.04		54.85	50.16
Gemini-3-flash 2026.04		53.85	52.73
Grok-4-Fast 2026.04		53.37	41.88
DeepSeek-V3 2026.04		51.92	49.04
GPT-4o 2026.04		51.92	44.81
Claude-Sonnet-4.5 2026.04		50.48	45.12
GPT-4o 2026.04		46.15	43.77
Qwen3-VL-Flash 2026.04		46.15	41.54
GPT-5.1 2026.04		44.23	48.54
MiniMax-M2.1 2026.04		43.29	43.13
GLM-4.7 2026.04		42.31	45.38
MiniMax-M2.1 2026.04		42.31	40.69
Qwen3.5-Plus 2026.04		37.82	44.7
Qwen3-Max 2026.04		33.76	38.65
Qwen3-VL-Max 2026.04		30.77	34.85
Qwen3-VL-235B-A22B 2026.04		28.85	31.69
Qwen3-Max 2026.04		26.92	30.15
Gemini-2.5-flash 2026.04		21.15	31.08
Qwen3.5-Plus 2026.04		17.31	27.5
Qwen3-VL-Plus 2026.04		15.38	27.69
Qwen3.5-Plus 2026.04		13.46	26.65