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

Table Fact Verification on TFV TabFact InfoTabs

88.16TabFact Accuracy

Gemini-2.5-Flash

Updated 1mo ago

Evaluation Results

Method	Links
Gemini-2.5-Flash 2026.04		88.16	91.43	89.8
V-tableR1 (4B) 2026.04		87.95	88.94	88.45
GPT-4.1 2026.04		87.32	92.43	89.88
GPT-4o 2026.04		85.16	88.75	86.96
V-tableR1 (2B) 2026.04		84.69	87.54	86.12
Qwen3-VL-4B (SFT) 2026.04		83.88	87.33	85.61
Qwen3-VL-32B 2026.04		82.43	78.25	80.34
Qwen3-VL-8B 2026.04		79.44	71.33	75.39
Qwen3-VL-2B (SFT) 2026.04		79.28	85.17	82.23
QVQ-72B 2026.04		77.68	74.64	76.16
InternVL-2.5-14B 2026.04		75.98	77.48	76.73
Qwen2.5-VL-72B 2026.04		73.45	72.82	73.14
Qwen3-VL-4B 2026.04		73.28	77.33	75.31
InternVL-2.5-8B 2026.04		72.92	74.67	73.8
Qwen3-VL-2B 2026.04		70.4	74.83	72.62
Table-LLaVA-13B 2026.04		65	66.91	65.96
Table-LLaVA-7B 2026.04		59.85	65.26	62.56
LLaVA-NeXT-7B 2026.04		34.18	41.23	37.71
LLaVA-1.5-13B 2026.04		28.37	37.34	32.86
LLaVA-1.5-7B 2026.04		23.25	32.34	27.8