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

Information Verification on InfoVerify proposed (real-world)

9.8Error Rate

xLAM-2-8B-FC

Updated 4d ago

Evaluation Results

Method	Links
xLAM-2-8B-FC 2026.04		9.8	19.21	10	33.98	30.67	20.55
Claude-Sonnet-4.5 2026.04		13.07	33.11	39	13.59	14	21.92
xLAM-2-8B-FC 2026.04		13.73	19.87	15	31.07	25.33	20.7
GPT-4o 2026.04		19.61	37.75	34	33.98	26.67	29.83
Claude-Sonnet-4.5 2026.04		23.53	31.79	53	30.39	41.33	35.06
ToolACE-2-8B 2026.04		23.53	16.56	23	33.01	28.67	24.51
GPT-4o 2026.04		24.18	39.74	31	32.04	32	31.81
ToolACE-2-8B 2026.04		24.18	32.45	37	44.66	31.33	32.88
Qwen3-8B 2026.04		25.49	39.07	34	22.33	38	32.27
Deepseek-chat 2026.04		28.76	43.05	37	22.33	40	34.86
Qwen3-8B 2026.04		30.07	35.76	31	25.24	43.33	33.79
Deepseek-chat 2026.04		32.03	39.07	43	26.21	34	34.86
APA-8B 2026.04		49.02	52.98	51	48.54	51.33	50.68
APA-8B 2026.04		53.59	51.66	57	55.34	53.33	53.88