List your company

Fact Verification on TabFact (held-in)

85.02AccuracyGemini-2.5-Pro
4.295225.252646.2167.1674Sep 21, 2025

Evaluation results

MethodLinks
Gemini-2.5-ProResolution=UNK2025.0985.02
OpenAI-o4-miniResolution=UNK2025.0984.7
QVQ-72B-PreviewResolution=Dyn.2025.0977.68
Qwen2-VL-72BResolution=Dyn.2025.0973.45
Qwen2-VL-7B-Table-R1Resolution=Dyn.2025.0973.4
GPT-4oResolution=UNK2025.0973.33
Qwen2-VL-7B-SFTResolution=Dyn.2025.0973.2
Table-LLaVA 13BResolution=3362025.0965
Qwen2-VL-2B-Table-R1Resolution=Dyn.2025.0960.9
Claude-3.5-SonnetResolution=UNK2025.0960.08
Table-LLaVA 7BResolution=3362025.0959.85
Qwen2-VL-2B-SFTResolution=Dyn.2025.0951.7
Qwen2-VL-7B-InsResolution=Dyn2025.0940
Qwen2-VL-2B-GRPOResolution=Dyn.2025.0922.7
Monkey 7BResolution=8962025.0922.56
LLaVA-v1.5 7BResolution=3362025.0918.9
DeepSeek-VL2 4.5BResolution=Dyn.2025.0913.65
Qwen2-VL-7B-GRPOResolution=Dyn.2025.0911.9
Qwen2-VL-2BResolution=Dyn.2025.098.9
mPLUG-Owl2 7BResolution=4482025.098.21
Qwen2-VL-7BResolution=Dyn.2025.097.4