Our new X account is live! Follow @wizwand_team for updates

Fine-grained Hallucination Detection on InFi-Check-FG (test)

92.34BAcc (Normalized)

InFi-Checker-Qwen

Updated 4d ago

Evaluation Results

Method	Links
InFi-Checker-Qwen 2026.01		92.34	87.74	94.92
InFi-Checker-Llama 2026.01		90.91	85.49	94.02
GPT-4o 2026.01		64.69	60.27	80.19
o3 2026.01		60.77	56.76	94.6
DeepSeek-V3.2-NoThink 2026.01		59.19	52.31	87.33
GPT-4.1 2026.01		58.91	55.13	94.87
Qwen3-8B 2026.01		50.49	44.78	87.22
Claude-3.7-Sonnet 2026.01		49.19	45.12	94.28
Qwen3-8B 2026.01		47.94	41.08	86.5
GPT-5 2026.01		46.35	42.28	92.58
Llama-3.1-8B-Instruct 2026.01		27.69	21.33	72.57
Llama-3.1-8B-Instruct 2026.01		23.79	18.12	79.41
InFi-Checker-Qwen 2026.01		0.9234	0.8774	0.9492
InFi-Checker-Llama 2026.01		0.9091	0.8549	0.9402
GPT-4o 2026.01		0.6469	0.6027	0.8019
o3 2026.01		0.6077	0.5676	0.946
GPT-4o 2026.01		0.605	0.5657	0.9497
DeepSeek-V3.2-NoThink 2026.01		0.5964	0.5394	0.8943
DeepSeek-V3.2-NoThink 2026.01		0.5919	0.5231	0.8733
GPT-4.1 2026.01		0.5891	0.5513	0.9487
o3 2026.01		0.58	0.5507	0.9548
GPT-4.1 2026.01		0.5445	0.4944	0.7817
Claude-3.7-Sonnet 2026.01		0.5307	0.4848	0.9221
Qwen3-8B 2026.01		0.5049	0.4478	0.8722
Claude-3.7-Sonnet 2026.01		0.4919	0.4512	0.9428
GPT-5 2026.01		0.4906	0.4441	0.9205
Qwen3-8B 2026.01		0.4794	0.4108	0.865
GPT-5 2026.01		0.4635	0.4228	0.9258
Llama-3.1-8B-Instruct 2026.01		0.2769	0.2133	0.7257
Llama-3.1-8B-Instruct 2026.01		0.2379	0.1812	0.7941