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

Question Answering on ARC Easy (Accuracy, Drop, TC2b)

94.82Accuracy

Qwen3-32B (+P)

84.752887.366489.9892.5936Jun 1, 2026
Updated 23h ago

Evaluation Results

MethodLinks
2026.06
94.82-0.4299.92
2026.06
94.78--
2026.06
94.61-0.4299.92
2026.06
94.36-0.4299.92
2026.06
94.32--
2026.06
94.19-0.4299.92
2026.06
89.31-9.1885.77
2026.06
88.34-9.1885.77
2026.06
86.08-9.1885.77
2026.06
85.14-9.1885.77