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

Science Question Answering on ARC Challenge (Accuracy, AVG, Delta)

58.1Accuracy

Qwen 8B (w/ LoopUS)

39.48444.31749.1553.983May 10, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
58.165.42.2
2026.05
57.768.61.7
2026.05
55.867-
2026.05
55.463.2-
2026.05
5462.11.8
2026.05
50.460.3-
2026.05
43.155.31.6
2026.05
40.253.7-