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

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

95.22Accuracy

Qwen3-32B (FP16)

74.815280.112685.4190.7074Jun 1, 2026
Updated 23h ago

Evaluation Results

MethodLinks
2026.06
95.22--
2026.06
93.77-1.7999.83
2026.06
93.69-1.7999.83
2026.06
93.6-1.7999.83
2026.06
93.43-1.7999.83
2026.06
93.09--
2026.06
81.31-17.4976.02
2026.06
80.03-17.4976.02
2026.06
76.44-17.4976.02
2026.06
75.6-17.4976.02