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

Question Answering on ARC (test) with Throughput Metrics

88.59Accuracy

FDM

55.081263.780672.4881.1794Dec 3, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
88.594.56
2025.12
88.455.59
2025.12
88.187.71
2025.12
87.4410.82
2025.12
87.3810.38
2025.12
87.0610.98
2025.12
86.684.58
2025.12
86.465.58
2025.12
867.72
2025.12
83.513.64
2025.12
83.453.73
2025.12
82.893.85
2025.12
82.5510.85
2025.12
80.9610.96
2025.12
78.1310.43
2025.12
76.194.01
2025.12
75.854.01
2025.12
71.843.98
2025.12
59.764.37
2025.12
59.615.58
2025.12
59.437.68
2025.12
58.3310.18
2025.12
58.2610.94
2025.12
56.3710.62