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

Science Question Answering on ARC Challenge

96Accuracy

Qwen-3-30B-A3B

7076.7583.590.25May 17, 2024Sep 5, 2024Dec 26, 2024Apr 17, 2025Aug 7, 2025Nov 27, 2025Mar 19, 2026
Updated 11d ago

Evaluation Results

MethodLinks
2026.02
96--
2026.02
95.2--
2026.03
95--
2025.04
94.7--
2026.02
94.5--
2026.02
94.3--
2025.04
94.3--
2025.04
94.3--
2026.03
94--
2026.02
93.6--
2026.02
93.5--
2026.02
93.4--
2026.03
93--
2026.02
92.3--
2026.01
91.1--
2026.02
89.8--
2026.01
89--
2026.01
88.9--
2025.04
88.9--
2026.01
88.4--
2026.01
88.2--
2026.01
88.2--
2026.01
88--
2026.03
88--
2026.01
87.7--
2025.04
87.7--
2026.02
86.1--
2026.02
85.9--
2026.03
85.8--
2026.01
85.4--
2025.10
84.98--
2026.02
84.7--
2025.10
84.64--
2026.02
84.3--
2025.04
83.7--
2026.01
83.2--
2026.01
83.2--
2025.04
82.8--
2025.10
82.42--
2024.07
82.25--
2025.04
82.1--
2024.07
80.59--
2024.07
80.59--
2026.01
80.5--
2026.01
80.2--
2026.03
79.6--
2026.03
79.6--
2026.03
78.8--
2026.03
78.8--
2026.03
78.6--
2026.03
78.4--
2026.02
78.21--
2024.05
78.2--
2026.01
78--
2024.05
77.8--
2026.03
77.8--
2026.03
77.4--
2026.03
77.4--
2024.05
77.2--
2026.03
77.2--
2026.03
77.2--
2026.03
77--
2026.03
77--
2026.03
77--
2026.03
76.6--
2026.03
76.4--
2026.03
76.4--
2026.03
76.4--
2026.02
76.23--
2024.05
76.2--
2026.03
76--
2026.03
76--
2026.03
75.8--
2026.03
75.8--
2026.02
75.5--
2024.05
75.2--
2026.02
75.17--
2024.05
74.6--
2024.05
74.4--
2026.03
74.2--
2024.05
74--
2026.03
73.4--
2026.02
73.29--
2026.03
73.2--
2026.03
73.2--
2024.05
72.6--
2026.03
72.6--
2026.03
72.4--
2026.03
72.4--
2024.07
72.3--
2026.03
72.2--
2026.03
72.2--
2026.03
72--
2026.03
71.6--
2026.03
71.6--
2026.03
71.6--
2026.03
71.4--
2026.03
71.2--
2026.03
71.2--
2026.03
71--
Showing 100 of 360 rows