List your company

Visual Question Answering on RealWorldQA xAI 2024 (test)

72.81AccuracyRobust-U1
37.325246.537655.7564.9624Jun 6, 2026

Evaluation results

MethodLinks
Robust-U1Category=Ours, Intensity=clean2026.0672.81
Robust-U1Category=Ours, Intensity=25%2026.0672.81
Robust-U1Category=Ours, Intensity=50%2026.0671.5
BAGELCategory=General MLLM, Intensity=clean2026.0668.76
BAGELCategory=General MLLM, Intensity=50%2026.0667.84
Robust-R1Category=Robust MLLM, Intensity=clean2026.0667.71
Robust-U1Category=Ours, Intensity=100%2026.0667.46
Robust-R1Category=Robust MLLM, Intensity=50%2026.0667.05
Robust-R1Category=Robust MLLM, Intensity=25%2026.0666.4
BAGELCategory=General MLLM, Intensity=25%2026.0665.75
Qwen2.5-VL-3BCategory=General MLLM, Intensity=clean2026.0665.22
Qwen2.5-VL-3BCategory=General MLLM, Intensity=25%2026.0664.96
Qwen2.5-VL-3BCategory=General MLLM, Intensity=50%2026.0663.39
Robust-R1Category=Robust MLLM, Intensity=100%2026.0663.26
BAGELCategory=General MLLM, Intensity=100%2026.0663.14
Qwen2.5-VL-3BCategory=General MLLM, Intensity=100%2026.0660.65
InternVL-4BCategory=General MLLM, Intensity=25%2026.0658.16
InternVL-4BCategory=General MLLM, Intensity=50%2026.0657.64
InternVL-4BCategory=General MLLM, Intensity=clean2026.0657.38
Gemma3-4BCategory=General MLLM, Intensity=clean2026.0655.42
InternVL-4BCategory=General MLLM, Intensity=100%2026.0654.9
Gemma3-4BCategory=General MLLM, Intensity=25%2026.0654.77
Gemma3-4BCategory=General MLLM, Intensity=50%2026.0653.72
Gemma3-4BCategory=General MLLM, Intensity=100%2026.0652.81
Robust CLIPCategory=Robust MLLM, Intensity=clean2026.0643.26
Robust CLIPCategory=Robust MLLM, Intensity=50%2026.0642.61
Robust CLIPCategory=Robust MLLM, Intensity=25%2026.0642.48
Robust CLIPCategory=Robust MLLM, Intensity=100%2026.0641.43
TeCoACategory=Robust MLLM, Intensity=clean2026.0640
TeCoACategory=Robust MLLM, Intensity=25%2026.0639.73
TeCoACategory=Robust MLLM, Intensity=50%2026.0639.47
TeCoACategory=Robust MLLM, Intensity=100%2026.0638.69